pexoai-agent
Fail
Audited by Snyk on Jun 16, 2026
Risk Level: HIGH
Full Analysis
HIGH W007: Insecure credential handling detected in skill instructions.
- Insecure credential handling detected (high risk: 1.00). The skill explicitly requires copying and sending full presigned asset URLs (including query parameters like OSSAccessKeyId/Signature) and shows an API key placeholder, which forces the agent to relay secret tokens verbatim in its output.
MEDIUM W021: Hidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
- Hidden Unicode characters detected (1 type(s) found)
Issues (2)
W007
HIGHInsecure credential handling detected in skill instructions.
W021
MEDIUMHidden or invisible Unicode characters detected (potential obfuscation or prompt injection).
Audit Metadata