user-stories-and-scenarios
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of instructional markdown files and evaluation data. There are no detections of prompt injection, credential exfiltration, malicious obfuscation, or persistence mechanisms. The content is strictly limited to generating text-based design documentation templates.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructions and evaluation cases (e.g., in evals/evals.json) define an attack surface where untrusted 'product intent' data is ingested to generate stories and scenarios. However, the risk is negligible as the skill lacks exploitable capabilities.\n
- Ingestion points: User-provided 'product intent' descriptions within input prompts.\n
- Boundary markers: None present in the skill instructions to delimit untrusted input.\n
- Capability inventory: None; the skill does not request or use any tools, shell execution, file system writes, or network access.\n
- Sanitization: No sanitization or validation of the input intent text is implemented.
Audit Metadata