oma-skill-creator

Pass

Audited by Gen Agent Trust Hub on May 3, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill employs common command-line tools including rg, find, awk, sed, git diff, and apply_patch. These are used locally to identify skill files, validate their structure against templates, and apply formatting updates.
  • [PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection as it ingests existing skill files and user-provided source material to generate new content.
  • Ingestion points: SKILL.md (ACQUIRE scene) reads analogous skills and user-provided input from the codebase and memory.
  • Boundary markers: While the skill enforces a rigid structure via its 'Guardrails' section, it does not implement explicit delimiters or instructions to ignore embedded prompts within the data it processes.
  • Capability inventory: The skill is authorized to perform file writes to the .agents/skills/ directory and execute text-processing utilities.
  • Sanitization: The instructions do not specify any sanitization or validation steps for the content of ingested files before they are interpolated into new skill definitions.
Audit Metadata
Risk Level
SAFE
Analyzed
May 3, 2026, 09:10 AM