find-skills

Pass

Audited by Gen Agent Trust Hub on Feb 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands via the npx skills CLI tool. This includes searching (find) and modifying the environment (add, update).
  • [REMOTE_CODE_EXECUTION]: The npx skills add <package> -g -y command is designed to download and install executable code from external repositories (e.g., GitHub). The use of the -y flag is particularly noteworthy as it skips user confirmation prompts during installation.
  • [EXTERNAL_DOWNLOADS]: The skill facilitates downloading content from skills.sh and various GitHub repositories. While it mentions trusted organizations like vercel-labs, it also allows for the installation of packages from any unverified third-party repository.
  • [PROMPT_INJECTION]: As an indirect injection surface, the skill processes external data (search results from npx skills find).
  • Ingestion points: Search results returned from the skills CLI which may contain descriptions or names controlled by third-party package authors.
  • Boundary markers: No explicit delimiters are used to separate CLI output from the agent's instructions.
  • Capability inventory: The skill possesses the ability to execute shell commands and install software globally (-g).
  • Sanitization: No sanitization or validation of the search results is performed before they are presented to the user or used in subsequent commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 24, 2026, 11:22 AM