prp-generator

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly mandates "External Research (Mandatory)" and WebSearch in SKILL.md and references/research_methodology.md, instructing the agent to fetch and document public URLs (e.g., GitHub, StackOverflow, official docs) whose user-generated/untrusted content will be read and used to shape implementation decisions, so it exposes the agent to untrusted third-party content.