ts-create-skill

Pass

Audited by Gen Agent Trust Hub on Aug 4, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill serves as a local judge for skill authoring. Its operations are confined to creating and updating source files within the intended project repository.
  • [DATA_EXPOSURE]: The skill reads existing local skill definitions to maintain repository consistency. This activity is restricted to the skill's development context and does not access sensitive system files or user credentials.
  • [PROMPT_INJECTION]: The instructions focus on technical writing standards and architectural hierarchy. There are no attempts to override safety filters or manipulate the underlying agent's core instructions.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes existing skill content to inform updates. While this represents a data ingestion surface, the risk is mitigated by the skill's narrow scope (local repository) and its prescriptive rules for technical output.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 4, 2026, 08:47 AM
Security Audit — agent-trust-hub — ts-create-skill