objective
Warn
Audited by Snyk on Apr 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). The skill's workflow (references/workflow.md and SKILL.md) explicitly instructs the agent to read GitHub issue bodies and recent comments (e.g., "gh issue view --comments", "Read the issue body", "Read recent comments", "erk objective view"), meaning it ingests untrusted, user-generated GitHub issue/comment content that can materially influence actions like updating statuses or closing objectives.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata