buildbot-reviewer
Warn
Audited by Snyk on Jun 24, 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’s required runtime inputs include “Issue title, body, and comments” from the Issue-to-PR workflow, which are outsider-authored free text (e.g., issue/discussion content by non-operating users) that the agent will ingest into its LLM context.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata