skills/ingpoc/skills/create-skill/Gen Agent Trust Hub

create-skill

Pass

Audited by Gen Agent Trust Hub on Jun 15, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [SAFE]: The skill serves as a scaffolding and governance tool for managing other skills. Its operations are limited to the local file system and involve standard file reading and writing within the project context.
  • [COMMAND_EXECUTION]: The skill executes local deterministic scripts (scripts/audit.py and scripts/validate.sh) via the Bash tool. These scripts perform static analysis of YAML frontmatter and file structures without using unsafe execution methods like eval() or fetching remote payloads.
  • [EXTERNAL_DOWNLOADS]: No remote network operations or package installations are performed. The skill relies entirely on local scripts and templates.
  • [DATA_EXFILTRATION]: While the skill reads local files to perform audits, it does not possess network capabilities to transmit data externally, and it does not access sensitive system paths.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 15, 2026, 09:45 AM
Security Audit — agent-trust-hub — create-skill