spec-loop-plan-work-breakdown
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user requests and read existing task files to generate or modify work breakdown artifacts.
- Ingestion points: Processes raw "User request" text and content from existing task-file paths as specified in SKILL.md.
- Boundary markers: The instructions lack explicit delimiters or warnings to the agent to treat external task-file content strictly as data, increasing the risk of the agent obeying instructions embedded within those files.
- Capability inventory: The skill has the capability to create new task files and modify existing project state files (backlog items).
- Sanitization: There is no evidence of input validation or sanitization for the content processed from external files or user input.
Audit Metadata