ClawAudit verdict
Amber_Url_to_Markdown
amber-url-to-markdown
The skill involves installing packages and potentially executing arbitrary code, but its primary function appears legitimate.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Permission integrity
package_install
Findings (6)
References child_process — can spawn system processes
RELEASE_3.2.0.md · code · child_process
Uses exec() — may execute shell commands
RELEASE_3.2.0.md · code · exec(
setuid — privilege escalation mechanism
scripts/amber_url_to_markdown_v4.py · prose · downgraded · setuid
HTTP request to bare IP address — common in malicious payloads
scripts/config.py · prose · downgraded · http://127.0.0.1
Python aiohttp session — async network access
scripts/async_fetcher.py · prose · downgraded · aiohttp.ClientSession
Python shutil file operation — copies/moves/deletes files
tests/test_amber_url_to_markdown.py · prose · downgraded · shutil.rmtree(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/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.