MCP server · trust report

io.github.rajamohan1950/cls-memory

1 check that ran failed — permission scope — so this release can’t be trusted as-is.

Publisher
io.github.rajamohan1950
Repository
github.com/rajamohan1950/CLSplusplus
Install
pypi:clsplusplus, pypi:clsplusplus, pypi:clsplusplus
Versions
4
Inspected
4 of 6 checks · 65%
Scored
2026-07-20 · 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 checks1 clean3 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

    pass25% of grade

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

    repository linkage verified

  • Credential hygiene

    warn15% of grade

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

    tests/test_abuse_guard.py: assigns a literal to api_key (sk-r…ey (len 20)) — non-provider secret literal; prefer environment intake. tests/test_agents.py: assigns a literal to secret (test…s! (len 33)) — non-provider secret literal; prefer environment intake. tests/test_window_limits.py: assigns a literal to api_key (cls_…ey (len 16)) — non-provider secret literal; prefer environment intake. tests/test_window_limits.py: assigns a literal to api_key (cls_…ey (len 15)) — non-provider secret literal; prefer environment intake. Reads secrets from the environment (e.g. src/clsplusplus/api.py) — 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/clsplusplus/abuse_guard.py: references a sensitive credential path (.aws/credentials) — the tool-poisoning exfiltration target. HIGH: shell/exec capability AND network egress together — download-and-execute risk (src/clsplusplus/api.py: subprocess.* call; src/clsplusplus/agents/eng_status.py: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (src/clsplusplus/api.py: subprocess.* call; src/clsplusplus/api.py: path traversal ('../') combined with file access). discloses shell/exec capability: src/clsplusplus/api.py: subprocess.* call discloses dynamic code execution: src/clsplusplus/api.py: uses eval/exec/__import__ discloses dynamic code execution: src/clsplusplus/webhook_dispatcher.py: uses eval/exec/__import__ discloses dynamic code execution: tests/test_agents.py: uses eval/exec/__import__ discloses dynamic code execution: tests/test_demo_llm.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: src/clsplusplus/api.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/clsplusplus/cli.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/clsplusplus/durable_log/file_wal.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/clsplusplus/durable_log/file_wal.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/clsplusplus/local_routes.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: src/clsplusplus/local_routes.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_durable_log.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_security.py: 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.rajamohan1950/[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.

    sends telemetry to third-party SDK (posthog) — disclosure, verify opt-in; 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
v7.19.0 · current2026-06-26 C72.54/6 · 65%