address-feedback
Warn
Audited by Snyk on Jun 26, 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 skill’s runtime workflow can ingest outsider-authored free text when the user provides a Public URL (web browsing) or an issue/PR/thread (GitHub connector /
gh issue view/gh pr view/ Slack connector), which the LLM reads into context as the “feedback source.”
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata