ClawAudit verdict
china-install-skills
Fetches from network AND uses eval/Function
Skill explicitly states it runs post-install initialization scripts 'without user awareness' (无需用户感知), silently configures weekly cron jobs, replaces the `clawhub install` command, and adds itself to PATH — all without prompting user consent, constituting undisclosed persistent system modification.
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.
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.
Fetches from network AND uses eval/Function — the remote-code-execution pattern (data-flow not verified)
LLM05 · LLM06 · ASI05
Permission integrity
file_read+write
Findings (4)
Recursive delete from root or home — destructive command
SKILL.md · code · rm -rf /
Pipe to bash — executes piped content as shell commands
SKILL.md · prose · downgraded · | bash
References sudo — requests elevated privileges
SKILL.md · prose · downgraded · sudo
Accesses shell history/config
scripts/init.sh · prose · downgraded · ~/.zshrc
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class A/B/F). Final tier capped at Caution — cannot be lifted by any downgrade, example-payload opt-in, or allowlist.
Permissions & capabilities
Requires 3 system binaries. (1 elevated: curl).
file_writedynamic_evalnetwork_out Thanks — recorded.