04-backlog-prioritization
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from local project files.
- Ingestion points: Reads
user_stories.md,vision.md, andstory_map.md(SKILL.md Core Instructions Step 1). - Boundary markers: Absent. The instructions do not define clear delimiters or warnings to ignore instructions embedded within the user story text or business goals.
- Capability inventory: The skill is authorized to read, search, and edit files (SKILL.md Capability and permission boundaries).
- Sanitization: There is no evidence of sanitization or validation of the text content extracted from the input files before it is processed by the agent.
Audit Metadata