recall-update

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

• Third-party content exposure detected (high risk: 0.75). SKILL.md:10-12 and SKILL.md:64-67 describe fetching GitHub release data (including free-form release notes body) at runtime via the GitHub Releases API, which is outsider-authored text that the skill then prints/relays into the agent’s LLM context.