io.github.TheAiSingularity/agentic-research

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.

• 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.

  Python build script has no build-time network/exec; repository linkage verified

• Credential hygiene

  pass15% of grade

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

  Reads secrets from the environment (e.g. core/rag/python/corpus.py) — the recommended intake shape. PASS = no static red flag; static analysis cannot prove the code honors env-based secret handling at runtime.

• 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 (engine/core/plugins.py: subprocess.* call; engine/core/pipeline.py: outbound HTTP/socket call). HIGH: shell/exec capability AND destructive filesystem writes together (engine/core/plugins.py: subprocess.* call; core/rag/python/corpus.py: open(…, 'w'/'a'/'x') write-mode file access). discloses shell/exec capability: engine/core/plugins.py: subprocess.* call discloses shell/exec capability: engine/core/plugins.py: os.system/os.popen/os.exec* call discloses dynamic code execution: engine/core/plugins.py: uses eval/exec/__import__ discloses broad/destructive filesystem access: core/rag/python/corpus.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: engine/benchmarks/runner.py: open(…, 'w'/'a'/'x') write-mode file access discloses broad/destructive filesystem access: engine/core/plugins.py: destructive filesystem call (shutil.rmtree/os.remove/etc.) 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.TheAiSingularity/[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 telemetry behavior — disclosure