ClawAudit verdict

tamp

88
🟢 Trusted
Low risk — reviewed by ClawAudit, behavior matches stated purpose

Executes processes AND makes external network calls

Local token compression proxy that sits between the agent and Anthropic API; the skill notes it does not store or read the API key and is open source MIT, with all behavior matching the stated cost-reduction purpose.

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.

0
security
50
transparency
70
maintenance

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.

Capability combination high

Executes processes AND makes external network calls — may exfiltrate command output

LLM02 · LLM06 · ASI03

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 critical

Possible hardcoded credential

SKILL.md · code · apiKey: "${ANTHROPIC_API_KEY}

Pattern match high

References child_process — can spawn system processes

SKILL.md · code · child_process

Permissions & capabilities

No declared permissions — minimal attack surface.

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