lesson-writer
Warn
Audited by Snyk on Aug 8, 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 SKILL.md Step 0 (load voice profile) the agent reads
${CLAUDE_SKILL_DIR}/voice-profile.mdby default or a user-named/tenant-providedvoice-profile.md, and that free text can affect the generated output at runtime.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata