Caveat verdict

xhs-viral-factory

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

Content generation tool sending user-specified local files to user-configured LLM API via HTTPS; explicitly discloses this data transfer in a Security Disclosure section.

⚠ 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.

55
security
100
transparency
90
maintenance

Findings (4)

Pattern match critical

Possible hardcoded credential

references/workflow.md · code · API_KEY="你的 API Key

Pattern match medium

Accesses shell history/config

references/workflow.md · prose · downgraded · ~/.zshrc

Pattern match low

pip3 install — installs Python packages at runtime

references/workflow.md · prose · downgraded · pip3 install

Pattern match low

Python os.getenv — reads environment variable

scripts/generate_xhs.py · prose · downgraded · os.getenv(

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: LLM_API_KEY).

Is this flag fair?

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