install-from-remote-library

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the download and installation of content from remote GitHub repositories using the npx ai-agent-skills command. It encourages defensive practices such as using --list to inspect the source and --dry-run to preview changes before execution.
  • [COMMAND_EXECUTION]: The skill utilizes the npx utility to execute the skill management tool. This involves running code from the npm registry and interacting with the local shell to perform installation tasks.
  • [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it processes data (skill names and collections) from untrusted remote repositories.
  • Ingestion points: The output of the npx ai-agent-skills install <owner>/<repo> --list command is ingested into the agent's context (SKILL.md).
  • Boundary markers: No explicit boundary markers or instructions to ignore embedded instructions in the remote data are present.
  • Capability inventory: The agent has the capability to execute shell commands via npx (SKILL.md).
  • Sanitization: There is no explicit sanitization or validation of the strings returned from the remote library before they are used in subsequent commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 04:39 PM