gepetto

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

• Third-party content exposure detected (high risk: 0.90). The skill's research step (references/research-protocol.md → Step 5) explicitly launches web-research subagents that use WebSearch/WebFetch to fetch and synthesize public web pages and URLs, which are untrusted third-party sources that the agent reads and incorporates into claude-research.md and later workflow steps.