architecture-review
Warn
Audited by Snyk on Aug 19, 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). Source SKILL.md specifies reading a user-supplied technical proposal (and linked repository/code/material) as review input in the workflow step “Read the goal, proposal, repository instructions, relevant current code, tests, schemas, configuration, and linked material,” so outsider-authored free text can be ingested.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata