seeking-skills
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill implements functionality to search for and download content from external GitHub repositories using the
/skill-seeker:seekand/skill-seeker:installcommands. - [REMOTE_CODE_EXECUTION]: The
/skill-seeker:installcommand facilitates the installation of external logic from community repositories, allowing for the introduction and execution of unverified third-party code within the agent's environment. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of unverified third-party skill content.
- Ingestion points: External GitHub repositories accessed via search and install commands (SKILL.md).
- Boundary markers: None identified in the provided documentation to distinguish between core instructions and fetched skill data.
- Capability inventory: The skill allows for the management, loading, and execution of functional extensions (skills) sourced from external environments.
- Sanitization: No explicit sanitization or verification of the fetched skill content is described.
Audit Metadata