Caveat verdict

agentos-mesh

88
🟢 Trusted
No high-risk patterns surfaced by the deep scan — automated capability review, not behavioral proof.

Accesses credentials AND writes files

Standard agent communication skill that installs a local CLI and configures credentials via config file or env vars; all behavior matches its stated purpose of inter-agent messaging with no evidence of exfiltration or manipulation.

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.

33
security
30
transparency
70
maintenance

What it does

These are capability combinations: each listed behavior occurs in the skill, but Caveat detects co-occurrence — it does not verify that one flows into another. Read the code to confirm a live chain.

Capability combination high

Accesses credentials AND writes files — may persist stolen credentials locally

LLM02 · LLM06 · ASI03

Permission integrity

Performs file operations but does not declare file-accessing binaries

file_read+write

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match medium

Accesses shell history/config

scripts/install.sh · prose · downgraded · ~/.zshrc

Pattern match medium

HTTP request to bare IP address — common in malicious payloads

scripts/mesh.sh · prose · downgraded · http://178.156.216.106

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