ClawAudit verdict

rss-reader

rss-reader-skill

88
🟒 Trusted
Low risk β€” reviewed by ClawAudit, behavior matches stated purpose

RSS aggregator with AI summarization that uses user-configured OpenAI/Zhipu API key and optional Feishu webhook; all data flows go to user-chosen destinations with no unexpected exfiltration.

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

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

28
security
30
transparency
80
maintenance

Permission integrity

Code accesses API keys/tokens but declares no environment variables

credential_access

Installs packages at runtime β€” transitive dependencies are not auditable

package_install

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md Β· code Β· API_KEY="δ½ ηš„ζ™Ίθ°±API Key

Pattern match medium

References webhook/callback URL

SKILL.md Β· code Β· WEBHOOK_URL

Pattern match medium

pip3 install β€” installs Python packages at runtime

SKILL.md Β· code Β· pip3 install

Pattern match low

Python os.getenv β€” reads environment variable

rss_reader.py Β· prose Β· downgraded Β· os.getenv(

Permissions & capabilities

No declared permissions β€” minimal attack surface.

credential_accessnetwork_inpackage_install

Is this flag fair?

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