find-skills
Pass
Audited by Gen Agent Trust Hub on Feb 28, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill initiates downloads of the "@openagentskills/find-skills" package from the npm registry and references external repositories on GitHub for skill installation.
- [COMMAND_EXECUTION]: The skill uses the npx utility to execute CLI commands. It performs operations such as searching, adding, and updating software, including global installations using the "-g" flag.
- [REMOTE_CODE_EXECUTION]: The skill is designed to fetch and run code from remote sources via the "npx skills add owner/repo@skill" command. The use of the "-y" flag bypasses user confirmation during the installation process.
- [PROMPT_INJECTION]: The skill provides an attack surface for indirect prompt injection. 1. Ingestion points: User-provided search queries passed to the npx skills find command. 2. Boundary markers: Absent. 3. Capability inventory: Execution of arbitrary code via npx, shell command execution, and global package installation. 4. Sanitization: Absent.
Audit Metadata