find-skills-wzr-999
Pass
Audited by Gen Agent Trust Hub on Mar 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
npx skillscommand-line tool to perform skill discovery, search, and installation tasks as documented in SKILL.md. - [EXTERNAL_DOWNLOADS]: It facilitates downloading agent skills from external sources, such as GitHub repositories, through the
npx skills addcommand. - [REMOTE_CODE_EXECUTION]: The installation process for external skills via the CLI involves downloading and executing code from third-party repositories, which is the primary purpose of this tool.
- [PROMPT_INJECTION]: The skill processes and displays external skill metadata retrieved from the registry, serving as an indirect prompt injection surface. * Ingestion points: Skill names, descriptions, and metadata returned by the
npx skills findcommand (SKILL.md). * Boundary markers: No specific delimiters or instructions are provided to the agent to treat search results as untrusted. * Capability inventory: The skill has command execution capabilities vianpxas outlined in SKILL.md. * Sanitization: There is no evidence of sanitization or validation of the external content before it is processed or presented.
Audit Metadata