MCP server · trust report

io.github.agentkitai/lore

2 checks that ran failed — supply chain and permission scope — so this release can’t be trusted as-is.

Publisher
io.github.agentkitai
Repository
github.com/agentkitai/lore
Install
pypi:lore-sdk, pypi:lore-sdk, pypi:lore-sdk, pypi:lore-sdk, pypi:lore-sdk
Versions
5
Inspected
4 of 6 checks · 65%
Scored
2026-07-21 · rubric 1.0.0

What we checked

Six static checks, weighted by risk. Every result reflects only what could be observed in the published package and repository — never intent.

6 checks0 clean4 flagged2 not inspected
  • Injection surface

    unscannable25% of grade

    Tool descriptions/manifest scanned for instruction-injection patterns (imperatives at the model, hidden text, 'ignore previous', data-exfil URLs).

    No tool descriptions, server instructions, prompts, or resources were fetched; nothing to scan for injection.

  • Supply chain

    fail25% of grade

    Package provenance: namespace verification, repo linkage, maintainer count, account age, postinstall scripts, typosquat distance.

    Python build script executes at build time: network call in build script

  • Credential hygiene

    warn15% of grade

    How the server takes secrets (env vs plaintext config vs hardcoded); secrets appearing in tool schemas.

    examples/redaction_demo.py: contains a hardcoded OpenAI API key (sk-a…no (len 30)) — in an example/sample file; verify it is not a real key. tests/test_edge_cases.py: contains a hardcoded OpenAI API key (sk-a…no (len 30)) — in an example/sample file; verify it is not a real key. tests/test_http_store.py: assigns a literal to api_key (lore…it (len 16)) — non-provider secret literal; prefer environment intake. tests/test_http_store.py: assigns a literal to api_key (lore…a0 (len 40)) — non-provider secret literal; prefer environment intake. tests/test_http_store.py: assigns a literal to api_key (lore…ue (len 19)) — non-provider secret literal; prefer environment intake. tests/test_http_store.py: assigns a literal to api_key (lore…st (len 12)) — non-provider secret literal; prefer environment intake. tests/test_ingest_adapters.py: assigns a literal to token (test…en (len 14)) — non-provider secret literal; prefer environment intake. tests/test_ingest_adapters.py: assigns a literal to secret (webh…et (len 14)) — non-provider secret literal; prefer environment intake. tests/test_progressive.py: assigns a literal to api_key (lore…st (len 12)) — non-provider secret literal; prefer environment intake. tests/test_redact.py: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) tests/test_redact.py: contains a hardcoded OpenAI API key (sk-a…12 (len 27)) — in an example/sample file; verify it is not a real key. tests/test_redact.py: contains a hardcoded JWT (eyJh…8U (len 92)) — in an example/sample file; verify it is not a real key. tests/test_redact.py: assigns a literal to secret (Zk9m…fG (len 32)) — non-provider secret literal; prefer environment intake. tests/test_redact.py: assigns a literal to secret (aB3c…2u (len 31)) — non-provider secret literal; prefer environment intake. tests/test_redact.py: assigns a literal to secret (X7kR…eF (len 31)) — non-provider secret literal; prefer environment intake. tests/test_redact.py: assigns a literal to secret (c2Vj…Q= (len 40)) — non-provider secret literal; prefer environment intake. tests/test_redact_integration.py: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) tests/test_redact_integration.py: contains a hardcoded OpenAI API key (sk-a…12 (len 27)) — in an example/sample file; verify it is not a real key. tests/test_redact_integration.py: contains a hardcoded JWT (eyJh…8U (len 92)) — in an example/sample file; verify it is not a real key. tests/persistence/test_redact_write.py: contains a hardcoded OpenAI API key (sk-a…12 (len 27)) — in an example/sample file; verify it is not a real key. ts/tests/redact.test.ts: embeds a PRIVATE KEY block. (in an example/sample file — lower severity, but a real key here still leaks.) ts/tests/redact.test.ts: contains a hardcoded OpenAI API key (sk-a…no (len 30)) — in an example/sample file; verify it is not a real key. ts/tests/redact.test.ts: contains a hardcoded JWT (eyJh…8U (len 92)) — in an example/sample file; verify it is not a real key. ts/tests/redact.test.ts: assigns a literal to secret (Zk9m…fG (len 32)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. hooks/lore-capture-end.sh) — the recommended intake shape.

  • Permission scope

    fail15% of grade

    Declared tools vs. breadth (filesystem, network, exec); flags shell-exec and unbounded filesystem access.

    HIGH: src/lore/integrate.py: references a sensitive credential path (/mcp.json) — the tool-poisoning exfiltration target. HIGH: shell/exec capability AND network egress together — download-and-execute risk (src/lore/bootstrap.py: subprocess.* call; hooks/lore-precompact.ts: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (src/lore/bootstrap.py: subprocess.* call; benchmarks/run_benchmarks.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: src/lore/bootstrap.py: subprocess.* call discloses shell/exec capability: src/lore/setup.py: subprocess.* call discloses shell/exec capability: src/lore/wrap.py: pty.spawn call discloses shell/exec capability: src/lore/cli/commands/_project.py: subprocess.* call discloses shell/exec capability: src/lore/cli/commands/capture.py: subprocess.* call discloses shell/exec capability: src/lore/cli/commands/dream.py: subprocess.* call discloses shell/exec capability: src/lore/cli/commands/server.py: subprocess.* call discloses shell/exec capability: src/lore/freshness/git_ops.py: subprocess.* call discloses shell/exec capability: src/lore/github/syncer.py: subprocess.* call discloses shell/exec capability: src/lore/services/graph_extraction.py: subprocess.* call discloses shell/exec capability: tests/test_capture_hook.py: subprocess.* call discloses shell/exec capability: tests/test_capture_prompt_hook.py: subprocess.* call discloses shell/exec capability: tests/test_dreams.py: subprocess.* call discloses shell/exec capability: tests/test_freshness.py: subprocess.* call discloses shell/exec capability: tests/test_lazy_server.py: subprocess.* call discloses shell/exec capability: tests/test_recent_integration.py: subprocess.* call discloses shell/exec capability: tests/cli/test_resolve_project.py: subprocess.* call discloses shell/exec capability: tests/cli/test_setup_claude_code_phase6g.py: subprocess.* call discloses dynamic code execution: tests/server/test_serve_cli.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: benchmarks/run_benchmarks.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: benchmarks/run_benchmarks.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/lore/bootstrap.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/integrate.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/retention.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/cli/commands/capture.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/lore/cli/commands/server.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/embed/local.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/embed/local.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/lore/export/snapshot.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/lore/github/state.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/lore/persistence/bootstrap.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/lore/server/routes/export.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/lore/ui/src/graph/interaction.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/lore/ui/src/panels/detail.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/lore/ui/src/panels/stats.js: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_dreams.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_export_integration.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_export_snapshot.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_freshness.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_import_json.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_openclaw_bridge.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_openclaw_bridge.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/server/test_secrets.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tools/openclaw-lore-bridge.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: ts/tests/redact.test.ts: path traversal ('../') combined with file access discloses broad/destructive filesystem access: ts/tests/remote-store.test.ts: path traversal ('../') combined with file access Capability DISCLOSURE, not a verdict: static analysis sees the primitive is present and reachable, not whether its use is attacker-controlled.

  • Version behavior

    unscannable10% of grade

    Diff of tool definitions between versions; new permissions or changed descriptions in a patch release (the postmark-mcp class).

    no prior version to diff (first sight of io.github.agentkitai/[email protected]); version-drift / rug-pull cannot be evaluated. Cold-start risk is covered by point-in-time checks (injection_surface, supply_chain, credential_hygiene), not here.

  • Transport config

    warn10% of grade

    Remote servers: TLS and auth mode (none/token/OAuth). Local servers: whether the manifest indicates it phones home.

    manifest/source references tracking behavior — disclosure

Version history

Each release plotted by grade against the safe line at B. A version that sinks below the line has lost its trusted standing — the shape of a rug-pull.

VersionPublishedGradeScoreInspectedChange
v1.4.2 · current2026-06-27 D47.54/6 · 65%