related-skill

Pass

Audited by Gen Agent Trust Hub on Sep 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill provides instructions for downloading and installing external packages from the inference.sh registry and the belt-sh/cli tool using the npx utility.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute npx skills commands for searching, listing, adding, and removing functional extensions within the environment.
  • [INDIRECT_PROMPT_INJECTION]:
  • Ingestion points: The skill reads external data from the inference.sh registry when performing searches or listing available extensions (e.g., in SKILL.md).
  • Boundary markers: No explicit delimiters are specified for handling the output of registry search results.
  • Capability inventory: The execution environment is limited to the npx skills command set via the Bash tool as defined in the allowed-tools frontmatter.
  • Sanitization: The skill relies on the standard output of the npx skills utility without additional sanitization layers for registry-provided descriptions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 2, 2026, 02:19 PM
Security Audit — agent-trust-hub — related-skill