auto-update
Warn
Audited by Snyk on Jul 15, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.75). The required workflow runs
git fetch/git log/optionally reads an updatedREADME.mdfrom a remote repository, so outsider-authored free text from the remote (commit messages/README) can be ingested into the agent context when summarizing “What’s New”.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata