resource-scout
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill facilitates the discovery and ingestion of data from untrusted external sources (GitHub, marketplaces, web search), creating a surface for indirect prompt injection. * Ingestion points: SKILL.md and README files from external repositories, marketplace descriptions mentioned in references/sources.md. * Boundary markers: Not present; instructions do not specify how to isolate or ignore embedded instructions within searched content. * Capability inventory: The search workflow suggests subsequent actions like modifying configuration files (.claude/settings.json) or installing third-party tools. * Sanitization: No sanitization or validation of external content is specified.
- [EXTERNAL_DOWNLOADS] (SAFE): The skill references numerous third-party websites and GitHub repositories. Although many of these do not belong to the defined Trusted Organizations, the skill acts strictly as an informational directory and does not automatically execute remote code or install packages through its own execution logic.
Audit Metadata