find-skills
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of external software packages from the agent skills ecosystem using the
npx skills addcommand. It references resources from established organizations such as Vercel Labs.- [COMMAND_EXECUTION]: The skill provides instructions for executing shell commands to manage system extensions, includingnpx skills find,npx skills check, andnpx skills add. The use of the-yflag in the installation command allows the agent to bypass interactive confirmation prompts, increasing the level of autonomy in executing remote code.- [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data (skill names and descriptions) from an external registry. - Ingestion points: Output from the
npx skills find [query]command inSKILL.md. - Boundary markers: None; the skill does not define delimiters or provide instructions to ignore potential commands embedded in skill descriptions.
- Capability inventory: Includes the ability to execute package installation commands (
npx skills add) which can modify the execution environment. - Sanitization: None; external metadata is presented directly to the agent for evaluation and presented to the user.
Audit Metadata