ClawAudit verdict

deep-research-via-gemini-cli-extension

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Both reads and writes files

Gemini CLI deep research workflow that starts a research job via MCP extension, writes a local poll script, and saves results to an Obsidian vault; executionSinkDetected reflects background polling of the user's own research task with no external exfiltration or injection.

Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.

48
security
70
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination medium

Both reads and writes files — verify scope is limited to intended directories

LLM06 · ASI02

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Findings (3)

Pattern match medium

Accesses system credential store

references/setup-guide.md · prose · downgraded · keychain

Pattern match medium

References child_process — can spawn system processes

scripts/dr-client.js · prose · downgraded · child_process

Pattern match medium

Uses spawn() — can execute external programs

scripts/dr-client.js · prose · downgraded · spawn(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

No declared permissions — minimal attack surface.

file_readfile_write
Check another skill Browse the registry Auditing your own skills or configs? Use the API