ClawAudit verdict
yunshang-aifei-cli-share
Accesses credentials AND makes external network calls
The skill embeds a hardcoded SM4 encryption key (`1097659710ff550f7da111309f64386b`) described as the unified frontend-backend key used to encrypt passwords before transmission, meaning anyone reading the skill can decrypt intercepted login credentials.
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
Permission integrity
network_out
credential_access
Findings (3)
Uses eval() — can execute arbitrary code
modules/captcha_solver.py · prose · downgraded · eval(
HTTP request to bare IP address — common in malicious payloads
SKILL.md · prose · downgraded · http://192.168.24.25
Python os.getenv — reads environment variable
aifei_api.py · prose · downgraded · os.getenv(
Permissions & capabilities
No declared permissions — minimal attack surface.
network_outnetwork_incredential_access Thanks — recorded.