agent-loops
Warn
Audited by Snyk on May 8, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's workflow (see SKILL.md sections for
specialist-reviewandtest-review-request) runs bundled scripts that invoke external LLM providers (Claude/Gemini/Codex), requires the agent to read their produced artifacts (REVIEW_FILE / REPORT_FILE) and then act on those findings (remediations, files to change, commit actions), which means untrusted third‑party model output is ingested and can materially influence tool use and next actions.
Issues (1)
W011
MEDIUMThird-party content exposure detected (indirect prompt injection risk).
Audit Metadata