banana-skill-finder

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

• Third-party content exposure detected (low risk: 0.10). The required workflow searches public third-party skill registries and code repositories (SkillsMP, skills.sh, GitHub API) whose returned contents and search results are authored by external developers and ingested as free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (medium risk: 0.30). The skill instructs the agent to query external search endpoints (SkillsMP API and GitHub API) and fetch web pages (skills.sh) at runtime to discover and recommend skills, relying on that retrieved external content for its operational behavior.