ClawAudit verdict
agentshield
Accesses system credential store AND makes external network calls
AgentShield is a documented AI agent security monitoring engine (Go binary) that runs locally on 127.0.0.1, uses bearer-token auth, rate limiting, and standard Sigma rules — all consistent with its stated AADR purpose; credentials are for LLM triage config, not exfiltrated.
Automated static analysis — not a human review. ClawAudit flags capabilities, not confirmed intent, and can produce false positives. Disagree with this verdict? Use Dispute below.
What it does
These are capability combinations: each listed behavior occurs in the skill, but ClawAudit detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.
Accesses system credential store AND makes external network calls
LLM02 · ASI03
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Permission integrity
network_out
credential_access
Findings (5)
Possible hardcoded credential
SKILL.md · code · token: "your-64-char-token-here
Accesses sensitive system files
SKILL.md · code · /etc/passwd
Accesses .ssh directory
SKILL.md · code · .ssh/
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://127.0.0.1
Popular HTTP library — network access
install.sh · prose · downgraded · got
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.
network_incredential_accesscredential_storenetwork_out Thanks — recorded.