ClawAudit verdict
claude-api
claude-api-cn
Chinese-localized Claude API documentation; no capabilities, purely reference documentation.
⚠ Flagged for review — coarse, uncorroborated signal, not a confirmed exploit. Review the config yourself before installing.
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.
Findings (6)
Possible hardcoded credential
curl/examples.md · code · API_KEY="your-api-key
Pipe to python — executes piped content as Python code
SKILL.md · prose · downgraded · | Python
Dynamic import() — loads module at runtime
go/claude-api.md · code · import (
"
Pipe to bash — executes piped content as shell commands
python/agent-sdk/README.md · prose · downgraded · | Bash
Instructs covert action — may act without user awareness
SKILL.md · prose · downgraded · silently
References agent configuration files
python/agent-sdk/README.md · prose · downgraded · CLAUDE.md
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A). 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.
Is this flag fair?
Thanks — recorded.