CreateSkill
Warn
Audited by Snyk on Aug 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (medium risk: 0.30). In the CreateSkill-related workflows (e.g., TestSkill Step 3), the agent reads target/local skill files (~/ .claude/skills/.../SKILL.md and workflow paths) and also incorporates user-authored test prompts/feedback into the runtime subagents, so attacker text can be ingested without selecting a specific trusted item first.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata