MCP server · trust report

io.github.romainsantoli-web/mcp-openclaw

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

Publisher
io.github.romainsantoli-web
Repository
github.com/romainsantoli-web/mcp-openclaw
Install
pypi:mcp-openclaw-extensions
Versions
1
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 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.

    tests/test_cov_100b.py: contains a hardcoded OpenAI API key (sk-A…AA (len 37)) — in an example/sample file; verify it is not a real key. tests/test_cov_100d.py: contains a hardcoded Slack token (xoxb…en (len 15)) — in an example/sample file; verify it is not a real key. tests/test_cov_100e.py: contains a hardcoded OpenAI API key (sk-p…ue (len 25)) — in an example/sample file; verify it is not a real key. tests/test_cov_hebbian.py: contains a hardcoded JWT (eyJh…8U (len 92)) — in an example/sample file; verify it is not a real key. tests/test_smoke.py: contains a hardcoded OpenAI API key (sk-a…89 (len 37)) — in an example/sample file; verify it is not a real key. Reads secrets from the environment (e.g. src/acp_bridge.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: shell/exec capability AND network egress together — download-and-execute risk (src/runtime_audit.py: subprocess.* call; src/delivery_export.py: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (src/runtime_audit.py: subprocess.* call; src/acp_bridge.py: destructive filesystem call (shutil.rmtree/os.remove/etc.)). discloses shell/exec capability: src/runtime_audit.py: subprocess.* call discloses shell/exec capability: tests/test_smoke.py: subprocess.* call discloses dynamic code execution: src/delivery_export.py: uses eval/exec/__import__ discloses dynamic code execution: src/security_audit.py: uses eval/exec/__import__ discloses dynamic code execution: tests/test_cov_mid.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: src/acp_bridge.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: src/advanced_security.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: src/gateway_fleet.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_config_helpers.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100b.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100c.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100d.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) discloses broad/destructive filesystem access: tests/test_cov_100d.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100f.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100g.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100h.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_100i.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: tests/test_cov_100i.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_acp_fleet_vs.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_extreme.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_final.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_mid.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_cov_ultra.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_hebbian_memory.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_market_research.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_models.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_patch_3_1.py: path traversal ('../') combined with file access discloses broad/destructive filesystem access: tests/test_smoke.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.romainsantoli-web/[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

    fail10% of grade

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

    source performs runtime self-update / download-and-execute (bypasses version_behavior); 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
v3.3.0 · current2026-03-03 D42.54/6 · 65%