Caveat verdict
agent-sbti
88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.
Performs a questionnaire and updates local configuration files with user consent, no harmful actions.
⚠ 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.
80
security
90
transparency
70
maintenance
Findings (2)
Pattern match medium
References agent configuration files
PLAN.md · code · agent_config
Pattern match medium
Uses exec() — may execute shell commands
scripts/apply.js · prose · downgraded · exec(
Permissions & capabilities
No declared permissions — minimal attack surface.
Is this flag fair?
Thanks — recorded.