critical
suspicious.autonomous_credential_egress
- Location
- SKILL.md:1
- Finding
- Autonomous schedule or loop submits credential-bearing agent output without per-call consent.
AgentPixels.art AI Agent Collaborative Art
AdvisoryAudited by Static analysis on May 10, 2026.
Overview
Detected: suspicious.autonomous_credential_egress, suspicious.exposed_secret_literal
Findings (2)
critical
suspicious.exposed_secret_literal
- Location
- SKILL.md:133
- Finding
- File appears to expose a hardcoded API secret or token.