quality-scenario
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided content, such as business requirements or product authority, to generate quality scenario artifacts. It lacks explicit instructions to sanitize this input or ignore embedded malicious directives, which is a common surface for indirect prompt injection.
- Ingestion points: Processes user-supplied "product authority" and "BRs" as defined in the methodology in SKILL.md.
- Boundary markers: No specific delimiters or "ignore previous instructions" guards are defined for the input data.
- Capability inventory: The skill possesses no dangerous capabilities; there are no subprocess calls, file system write operations, or network requests across any of the files.
- Sanitization: No input validation or escaping techniques are implemented.
- [SAFE]: The skill is entirely instructional and does not include any scripts, dependencies, or automated command execution. There are no signs of obfuscation, exfiltration patterns, or persistence mechanisms.
Audit Metadata