find-skills
Warn
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill directs the agent to run npx skills commands to search for and manage agent extensions.
- [EXTERNAL_DOWNLOADS]: The skill fetches content from the npm registry and arbitrary GitHub repositories during the discovery and installation process.
- [REMOTE_CODE_EXECUTION]: The npx skills add command facilitates the installation of code from remote sources. The inclusion of the -y flag bypasses confirmation prompts, which could lead to the automatic execution of untrusted code.
- [PROMPT_INJECTION]: The skill demonstrates a vulnerability to indirect prompt injection by interpolating user-controlled input into a shell command.
- Ingestion points: User queries are passed directly into the [query] parameter in SKILL.md.
- Boundary markers: No delimiters or safety instructions are provided to sanitize the user-provided search term.
- Capability inventory: The skill has access to shell execution and package management via npx.
- Sanitization: There is no evidence of input validation or escaping for the user-provided query.
Audit Metadata