find-skills
Fail
Audited by Gen Agent Trust Hub on Apr 20, 2026
Risk Level: HIGHCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill provides instructions for the agent to download and install arbitrary packages using the
npx skills addcommand. - [COMMAND_EXECUTION]: The instructions involve executing shell commands to perform package management tasks, such as searching for and updating software via the Skills CLI.
- [REMOTE_CODE_EXECUTION]: The skill specifically recommends using the
-yflag with the installation command, which bypasses user confirmation prompts and allows for the silent installation of external code. - [EXTERNAL_DOWNLOADS]: The agent is directed to fetch code and configuration from the
skills.shdomain and various third-party GitHub repositories. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface when handling external data.
- Ingestion points: Data returned from the
npx skills findsearch command (SKILL.md). - Boundary markers: Absent; the instructions do not include delimiters or warnings to ignore instructions embedded in search results.
- Capability inventory: Full shell execution and package installation capabilities (
npx skills add). - Sanitization: Absent; there is no specified validation or filtering for search results retrieved from the external registry.
Recommendations
- AI detected serious security threats
Audit Metadata