skills/toolshell/skills/related-skill/Gen Agent Trust Hub

related-skill

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes Bash permissions to run the npx skills utility for searching and managing agent extensions.
  • [EXTERNAL_DOWNLOADS]: The skill fetches data and packages from the inference.sh domain as part of its core functionality.
  • [REMOTE_CODE_EXECUTION]: Using npx skills add facilitates the installation and execution of remote code packages on the system.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted data from the inference.sh registry. Ingestion points: Results from npx skills search and npx skills list. Boundary markers: None present. Capability inventory: Permission to execute Bash commands including npx skills add. Sanitization: None detected for registry metadata.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:18 PM
Security Audit — agent-trust-hub — related-skill