release-notes
Warn
Audited by Snyk on Jun 17, 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). The skill runs
gh pr list ... --json number,title,labels,mergedAtand then uses the PRtitle(and labels) to generate the[Unreleased]changelog entries, so it ingests outsider-authored free text from GitHub PRs (titles/labels) into the agent’s LLM context via the runtime PR-listing output.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata