Caveat verdict
tars-vault
agent-scif
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
The skill only spawns a clean‑room sub‑agent and forwards commands, never reading or exfiltrating vault contents.
⚠ 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.
95
security
90
transparency
70
maintenance
Findings (2)
Pattern match low
Popular HTTP library — network access
scripts/vault_cleanroom.py · prose · downgraded · got
Pattern match low
Blob URL — may embed executable content
scripts/vault.py · prose · downgraded · blob:
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.