01-user-story-generation
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted project documentation from external files to generate requirements artifacts, which presents an attack surface for indirect prompt injection.
- Ingestion points: The skill reads multiple files from the
projects/<ProjectName>/_context/directory, includingvision.md,features.md,personas.md,glossary.md, andquality_standards.md(documented inSKILL.md). - Boundary markers: The instructions do not specify any delimiters or safety warnings to ensure the agent ignores potentially malicious instructions embedded within the source project documents.
- Capability inventory: The skill is capable of reading and writing markdown and Mermaid files in the project directory (documented in
SKILL.md); it does not have network access or shell execution permissions. - Sanitization: No validation, filtering, or sanitization logic is implemented for the content ingested from the project context files.
- [NO_CODE]: The skill is entirely composed of markdown instructions, reference documentation, and templates; no executable scripts, binaries, or automated code components are included.
Audit Metadata