shape
Warn
Audited by Snyk on Nov 19, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (low risk: 0.10). The required workflow reads the user's own topic argument, local files, and read-only subagent searches, but when it writes decisions to "the issue or the pull request body" (line 41) it may first need to read an existing GitHub issue or PR body, which outsiders can author on public repos, so this is a conditional, agent-selected fetch rather than a monitored inbox.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata