mpm-migrate
Warn
Audited by Snyk on Jul 13, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.70). SKILL.md:38-40 requires reading the selected subskill’s body text (motivation/gotchas/notes) and frontmatter at runtime, and those subskill SKILL.md files are outsider-authored relative to this router skill (i.e., not authored by the operating user), which can include free-form text that the LLM will ingest as context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata