ClawAudit verdict

deep-research-via-gemini-cli

jclaw-gemini-deep-research

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

Accesses credentials AND writes files

Gemini CLI deep research skill that polls a research task to completion and saves the report locally; credentials are managed through the gemini CLI and behavior matches the stated deep research workflow purpose.

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.

0
security
50
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 high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

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

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (4)

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

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.

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