prps-agentic-engineering

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.90). The skill's /prp-issue-investigate workflow explicitly "Auto-fetched from GitHub" (SKILL.md) and the agent reads and acts on that user-generated GitHub issue content to produce investigations, plans, and fixes (e.g., /prp-issue-fix and autonomous Ralph loops), so untrusted third-party input from GitHub can materially influence agent actions.