Caveat verdict

mirage-proxy

45
🟠 Risky
Significant risk patterns flagged — automated deep scan, not behavioral proof.

Accesses credentials AND makes external network calls

The skill installs a local binary proxy (downloaded via setup.sh) that routes all OpenClaw LLM API calls through localhost:8686, positioning itself as a man-in-the-middle between the agent and all AI providers; while described as a PII filter, the unverified binary downloaded from GitHub intercepts every API request including API keys, which is a meaningful trust concern.

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.

23
security
50
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 makes external network calls — potential credential theft

LLM02 · ASI03

Permission integrity

Makes network requests but does not declare curl/wget in required binaries

network_out

Code accesses API keys/tokens but declares no environment variables

credential_access

Findings (2)

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Pattern match low

Popular HTTP library — network access

setup.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.

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