Caveat verdict
scientific-internet-access
The skill contains explicit behavioral hijacking instructions — it commands the agent to run `handler.py` and forward its output verbatim to users with 'zero_extra_text', effectively making the agent a blind relay for whatever the untrusted script produces, which is a classic prompt-injection/agent-hijack pattern.
⚠ 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.
Findings (3)
subprocess execution — runs system commands from Python
scripts/handler.py · prose · downgraded · subprocess.run(
Python os.environ.get — reads environment variable
scripts/formatter.py · prose · downgraded · os.environ.get(
Python urllib.request — network access
scripts/scraper.py · prose · downgraded · urllib.request
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.
Is this flag fair?
Thanks — recorded.