guided-production-wizard

Pass

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests instructions from a reference file, which is a potential vector for indirect prompt injection.
  • Ingestion points: Reference to ../../references/GUIDED_PRODUCTION_WIZARD.md in SKILL.md.
  • Boundary markers: None identified in the skill instructions.
  • Capability inventory: Support for shell tools like bash and shellcheck.
  • Sanitization: No explicit validation or filtering of the external reference content.
  • [DYNAMIC_EXECUTION]: The skill describes a workflow involving the generation of executable scripts.
  • Evidence: Instructions for the agent to 'Produce a Markdown guide alongside any executable wizard script' and run linters like shellcheck.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 19, 2026, 08:41 AM