build-loop-claude-code

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the repository's plan files.
  • Ingestion points: The skill explicitly searches the repository for roadmap, refactor plan, or task list files and executes tasks found within them (SKILL.md).
  • Boundary markers: No boundary markers or 'ignore' instructions are used to separate task descriptions from the agent's operational instructions.
  • Capability inventory: The skill allows the agent to modify code, run security review tools, and execute the full project test suite (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the task content read from the files before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 02:12 AM