exa-code-search

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

• Third-party content exposure detected (high risk: 0.90). SKILL.md explicitly states the skill finds code snippets and docs from public sites like GitHub and StackOverflow and uses the exa-code.get_code_context_exa call to retrieve that content, so the agent ingests and acts on untrusted, user-generated web content.