Caveat verdict

claude-code-custom-model-proxy

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

Accesses agent memory/notes AND makes external network calls

Sets up a local Python proxy on localhost:4002 that converts Anthropic API format to OpenAI format for custom model providers; entirely local, legitimate interoperability tool with no exfiltration.

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.

0
security
90
transparency
90
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 critical

Accesses agent memory/notes AND makes external network calls — may leak personal data

LLM02 · LLM07 · ASI03 · ASI06

Capability combination high

Accesses agent memory AND makes external network calls — may leak conversation history

LLM02 · LLM07 · ASI06

Permission integrity

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

network_out

Accesses agent memory/configuration files

agent_memory

Findings (4)

Pattern match critical

Possible hardcoded credential

SKILL.md · code · API_KEY="fake-key

Pattern match critical

Pipe-to-python pattern — remote code execution risk

SKILL.md · code · curl -s http://127.0.0.1:4002/v1/models | python

Pattern match critical

Pipe to python — executes piped content as Python code

SKILL.md · code · | python3

Pattern match high

HTTP request to bare IP address — common in malicious payloads

SKILL.md · code · http://127.0.0.1

Permissions & capabilities

No declared permissions — minimal attack surface.

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