apc-orchestrate
Fail
Audited by Snyk on Nov 19, 2026
Risk Level: CRITICAL
Full Analysis
CRITICAL E004: Prompt injection detected in skill instructions.
- Potential prompt injection detected (medium risk: 0.30). The skill's only content is a pointer that tells the agent to follow an external workflow file "exactly as written," so its actual behavior (worker profiles, wave protocol, completion message) is hidden from the user in this skill, which is sketchy even though no malicious intent is visible.
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The skill's only instructions are a pointer to
.agents/workflows/apc-orchestrate.md, which is not in the input, so any outsider exposure would come from subagent workers that may search or fetch arbitrary web content, a path the agent must actively trigger.
Issues (2)
E004
CRITICALPrompt injection detected in skill instructions.
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata