Caveat verdict

boot-resume

88
๐ŸŸข Trusted
No high-risk patterns surfaced by the deep scan โ€” automated capability review, not behavioral proof.

Session recovery skill that scans local JSONL session files to detect interrupted agent turns and schedules resume commands; all operations are local system reads matching the stated crash recovery purpose.

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

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

48
security
90
transparency
90
maintenance

Findings (3)

Pattern match critical

Recursive delete from root or home โ€” destructive command

SKILL.md ยท code ยท rm -rf ~

Pattern match high

Pipe to python โ€” executes piped content as Python code

scripts/boot-resume-check.sh ยท prose ยท downgraded ยท | python3

Pattern match low

Popular HTTP library โ€” network access

scripts/boot-resume-check.sh ยท prose ยท downgraded ยท got

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class B). Final tier capped at Caution โ€” cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 2 system binaries.

Is this flag fair?

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