Caveat verdict
research-assistant
bear-research-enricher
The skill uses the `gifgrep` skill and makes API calls, but does not exhibit clearly malicious behavior.
⚠ 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 (2)
Pipe to python — executes piped content as Python code
scripts/enrich_notes.sh · prose · downgraded · | python3
Instruction-prose smuggling shape detected: collects a sensitive target ("api_key") and emits it outward ("Append"). Phrased as prose with no trigger tokens — a semantic prompt-injection / data-exfil pattern the syntactic scanners can't see. Final tier capped at Caution; review the instructions before installing.
SKILL.md · 1. **Fetch notes**: Run `grizzly open-tag --name "待整理" --enable-callback --json --token-file ~/.config/grizzly/token` to list all notes with the tag. 2. **For e
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B). 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.