workflow-refactor

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes instructions to run a local utility script node .claude/scripts/lib/workflow-skill-contract.cjs --write for internal block regeneration. This is a standard administrative task for this skill.
  • [INDIRECT_PROMPT_INJECTION]: The workflow involves ingesting data from external files such as docs/project-config.json, .claude/workflows.json, and the source code being refactored. Maliciously crafted content in these files could theoretically influence agent behavior.
  • Ingestion points: Project configuration files and the code targeted for refactoring.
  • Boundary markers: The skill does not define specific delimiters for separating data from instructions in the files it reads.
  • Capability inventory: The skill utilizes file reading, local script execution, and the ability to spawn subagents (spawn_agent).
  • Sanitization: No explicit sanitization or filtering logic is provided for the content ingested during the refactoring process.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 10:11 AM