014-agile-user-story
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided input that may contain content pasted from external sources (e.g., issue descriptions or chat logs), which presents a potential surface for indirect prompt injection.
- Ingestion points: Questionnaire responses collected during the workflow described in
SKILL.mdandreferences/014-agile-user-story.md. - Boundary markers: The skill employs a strict one-by-one questioning format which naturally segments user input.
- Capability inventory: The skill does not possess capabilities for network operations, sensitive file system access, or arbitrary command execution.
- Sanitization: Explicit safeguards are included, requiring the agent to treat responses as structured facts only, ignore any instructions embedded within answers, and request sanitized summaries if the user provides raw external text.
Audit Metadata