find-skills
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill facilitates the installation and execution of external code packages using the
npx skills addcommand. While this is the intended purpose of the skill, it allows the agent to fetch logic from public repositories. - Evidence: The skill provides the command
npx skills add <owner/repo@skill> -g -yto install packages globally while bypassing the command-line confirmation prompts. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it searches a public index and processes the results.
- Ingestion points: The agent is instructed to run
npx skills find [query]and present the resulting metadata to the user. - Boundary markers: There are no instructions to use delimiters or ignore embedded commands when processing search result descriptions.
- Capability inventory: The agent has the capability to run shell commands and install/execute the packages it discovers.
- Sanitization: The instructions do not specify any validation or sanitization for the content returned by the search command.
Audit Metadata