breaking-into-product
Warn
Audited by Snyk on Jul 16, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is embedded directly in the skill’s required content via guest quotes in
SKILL.md(e.g., Annie Pearl/others), which the agent would read into its LLM context as part of the skill’s prompt.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata