ghpm-shared
Warn
Audited by Snyk on Mar 12, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required startup/cache flow (SKILL.md + references/cache.md) automatically re-fetches GitHub Project items via the
gh project item-listcommand, ingesting user-generated issue/project content that the agent reads and uses to drive recommendations and session actions, creating a clear vector for indirect prompt injection.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata