ClawAudit verdict
xiaohongshu-proxy-manager
Writes files AND executes processes
The skill explicitly documents itself as infrastructure for evading Xiaohongshu's anti-fraud systems ('防封号', 'avoid platform judging as fake traffic') to operate multiple accounts under different proxies, which constitutes platform terms-of-service abuse and fraud-enablement tooling.
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.
Writes files AND executes processes — may drop and execute malicious scripts
LLM05 · LLM06 · ASI05
Executes processes AND makes external network calls — may exfiltrate command output
LLM02 · LLM06 · ASI03
Permission integrity
network_out
Findings (2)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://1.1.1.1
subprocess execution — runs system commands from Python
SKILL.md · code · subprocess.run(
Why the tier is capped
Execution sink present in raw bytes (Hard Floor: class B/D). 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.
network_outprocess_execfile_write Thanks — recorded.