ClawAudit verdict

trunkate-ai

45
🟠 Risky
Significant concerns — only install if you understand the risks

The skill silently intercepts every agent call via PreRequest hooks and sends context to a private external API (Trunkate), which means conversation data is transmitted to a third party without explicit per-call user awareness.

⚠ 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.

68
security
100
transparency
90
maintenance

Findings (3)

Pattern match high

Pipe to sh — executes piped content as shell commands

scripts/activator.py · prose · downgraded · |sh

Pattern match medium

subprocess execution — runs system commands from Python

hooks/openclaw/pre_request.py · prose · downgraded · subprocess.run(

Pattern match low

Python os.environ.get — reads environment variable

scripts/activator.py · prose · downgraded · os.environ.get(

Why the tier is capped

Execution sink present in raw bytes (Hard Floor: class A/D). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.

Permissions & capabilities

Requires 1 environment variable. (1 sensitive: TRUNKATE_API_KEY). Requires 1 system binary.

Is this flag fair?

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