requirement-workflow

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes several bash scripts (e.g., init-workflow.sh, advance-stage.sh) that perform file system operations, such as creating directories and updating YAML configuration files using standard utilities like sed and grep to maintain workflow state.\n- [PROMPT_INJECTION]: The skill's architecture relies on reading and following instructions from local project files, which presents a surface for indirect prompt injection.\n
  • Ingestion points: Documentation files such as spec.md, tasks.md, and design.md, as well as configuration files like hooks.yaml.\n
  • Boundary markers: Absent; the prompts do not use specific delimiters or instructions to prevent the AI from adopting commands or directions found within these user-editable markdown files.\n
  • Capability inventory: The system can transition workflow states, modify project files, and dynamically 'launch' or 'inject' additional agents/skills based on configuration strings.\n
  • Sanitization: Absent; the content within the ingested markdown and YAML files is used to drive AI behavior without being filtered for instructional or adversarial patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 06:31 PM