ClawAudit verdict
sano-intel
sanointel-by-probevc
Accesses credentials AND makes external network calls
A Chinese healthcare industry intelligence API skill sending queries with an API key to documented endpoints; data access is read-only and consistent with the stated market intelligence 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.
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.
Accesses credentials AND makes external network calls — potential credential theft
LLM02 · ASI03
Accesses credentials AND writes files — may persist stolen credentials locally
LLM02 · LLM06 · ASI03
Permission integrity
network_out
file_read+write
credential_access
Findings (2)
HTTP request to bare IP address — common in malicious payloads
SKILL.md · code · http://47.102.196.1
Accesses shell history/config
SKILL.md · code · ~/.zshrc
Permissions & capabilities
No declared permissions — minimal attack surface.
file_writenetwork_outcredential_access Thanks — recorded.