Caveat verdict

double-search

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Parallel search skill using Tavily and Kimi APIs with clearly documented behavior; reads API keys from env vars for their intended purpose and sends queries to the two named search services.

⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.

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

40
security
50
transparency
70
maintenance

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Installs packages at runtime — transitive dependencies are not auditable

package_install

Findings (5)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="tvly-xxxxxxxxxxxx

Pattern match low

Python os.getenv — reads environment variable

__init__.py · prose · downgraded · os.getenv(

Pattern match low

Python aiohttp session — async network access

__init__.py · prose · downgraded · aiohttp.ClientSession

Pattern match low

POSTs data to external URL

__init__.py · prose · downgraded · .post( "https://

Pattern match low

pip3 install — installs Python packages at runtime

install.sh · prose · downgraded · pip3 install

Why the tier is capped

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

Permissions & capabilities

Requires 2 environment variables. (2 sensitive: TAVILY_API_KEY, KIMI_API_KEY). Requires 1 system binary.

network_outpackage_installcredential_access

Is this flag fair?

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