workflow-orchestration
Pass
Audited by Gen Agent Trust Hub on Feb 26, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill uses a bootstrap process in 'references/bootstrap.md' to ensure its own instructions are persisted across sessions by modifying project configuration files like 'AGENTS.md' or 'CLAUDE.md' with a mandatory 'Discipline' block.
- [PROMPT_INJECTION]: The skill establishes an automated feedback loop where user corrections are stored in 'docs/tasks/lessons.md' to influence future behavior, representing a surface for indirect prompt injection. • Ingestion points: User corrections and bug reports. • Boundary markers: None present. • Capability inventory: Modification of local markdown files and instructions. • Sanitization: No sanitization or validation of user input before rule creation.
- [NO_CODE]: The skill consists exclusively of instructional markdown files and contains no executable scripts or code.
Audit Metadata