find-skills
Pass
Audited by Gen Agent Trust Hub on Feb 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill guides the agent to execute shell commands using the
npxutility to invoke theskillsCLI for searching, checking updates, and modifying the environment. - [REMOTE_CODE_EXECUTION]: It leverages
npx skills addto download and install executable code from external sources like GitHub. The instructions encourage the use of the-yflag to automate installation by bypassing interactive confirmation prompts. - [EXTERNAL_DOWNLOADS]: The skill references the
skills.shregistry and GitHub for retrieving package metadata and code. These interactions are associated with the tool's primary purpose of package management. - [PROMPT_INJECTION]: An indirect prompt injection surface exists as the agent processes results from the
npx skills findcommand, which contains untrusted external data. - Ingestion points: Search results from the external
skillsCLI tool. - Boundary markers: None provided in the instruction set to delimit search results.
- Capability inventory: The agent can perform shell execution and install new code packages.
- Sanitization: No validation or escaping of external search result content is described before presentation or action.
Audit Metadata