agt-security — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited agt-security (Agent Skill) and scored it 87/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 3 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 3 flagged
The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
This skill contains tools and reference materials to manage secure local execution sandboxes, verify process hygiene limits, and rotate cryptographic bus keys.
To verify that the sub-agent execution environment complies with AGT process hygiene or containerized sandboxing:
python3 plugins/cli-agents/scripts/agt_ops.py verify-sandboxThis performs:
ANTHROPIC_API_KEY, PYTHONPATH) are scrubbed inside subprocesses.To generate or rotate the HMAC symmetric key used to sign messages across the local control plane:
python3 plugins/cli-agents/scripts/agt_ops.py rotate-keyKeys are rotated dynamically and written to ${CLAUDE_PROJECT_DIR}/context/exploration/.secrets/session_hmac.key with restricted 0600 permissions.
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.