find-skills

Warn

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill provides instructions for downloading and installing arbitrary code from remote repositories.
  • Evidence: Instructs the agent to use npx skills add <owner/repo@skill> -g -y. The use of the -y flag is particularly concerning as it typically bypasses user confirmation prompts during the installation process, allowing for the silent execution of third-party code.
  • [EXTERNAL_DOWNLOADS]: The skill interacts with an external registry and third-party sources to fetch executable content.
  • Evidence: Connects to https://skills.sh/ to browse and search for skills, and downloads packages from various GitHub repositories via the npx skills tool.
  • [COMMAND_EXECUTION]: The skill relies on executing shell commands to manage its ecosystem.
  • Evidence: The skill defines several shell-based operations including npx skills find, npx skills add, npx skills check, and npx skills update to perform its primary functions.
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection via external search results.
  • Ingestion points: The output of npx skills find [query] which fetches data from the external skills.sh registry.
  • Boundary markers: None. There are no delimiters or instructions to treat the search results as untrusted data.
  • Capability inventory: The skill has the capability to execute shell commands (npx), install packages, and write to the global environment (-g flag).
  • Sanitization: No sanitization or validation of the data returned by the search command is documented before the agent processes and acts upon that information.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Aug 4, 2026, 11:26 AM