Caveat verdict
claw-news
This news aggregation skill fetches from RSS feeds and AI search APIs using user-configured API keys; all data flows are for the stated purpose of generating news digests and no exfiltration patterns are present.
⚠ 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.
Permission integrity
package_install
Findings (7)
Possible hardcoded credential
references/claude_api.md · code · api_key="YOUR_ANTHROPIC_API_KEY
Pipe to python — executes piped content as Python code
references/rss_examples.md · code · | python
subprocess execution — runs system commands from Python
references/rss_examples.md · code · subprocess.run(
POSTs data to external URL
references/minimax_api.md · code · .post(
"https://
Python urllib.request — network access
rss/kimi_client.py · prose · downgraded · urllib.request
Python os.getenv — reads environment variable
rss/kimi_client.py · prose · downgraded · os.getenv(
Popular HTTP library — network access
rss/rss_fetcher.py · prose · downgraded · Got
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.
package_install Is this flag fair?
Thanks — recorded.