story-readiness
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs validation of local markdown files using Read, Glob, and Grep tools, adhering to a read-only execution model.
- [SAFE]: No network activity, external downloads, or remote code execution patterns were detected.
- [SAFE]: The skill uses the Task tool to spawn a standard project-specific gating mechanism (QL-STORY-READY), which is a platform-authorized behavior for coordinating sub-agent workflows.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted story content from project directories, which acts as a potential injection surface.
- Ingestion points: The skill reads story files from
production/epics/**/*.mdandproduction/sprints/based on user arguments. - Boundary markers: No explicit boundary markers or delimiters are used when processing the text of the story files.
- Capability inventory: Capabilities are limited to Read, Glob, Grep, AskUserQuestion, and Task (spawning sub-agents). No write or shell-execution capabilities are present.
- Sanitization: The skill looks for specific design markers (e.g., 'TBD', 'TODO', 'UNRESOLVED') but does not perform general sanitization of the input text before processing.
Audit Metadata