sdlc-create-intent
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes 'informal requests' from potentially untrusted sources to generate intent artifacts. This creates a risk where malicious instructions embedded in a software request could influence the agent's behavior during the documentation process.
- Ingestion points: Processes informal software requests provided as input (SKILL.md).
- Boundary markers: The instructions lack specific delimiters or guidelines to treat the input request as data rather than instructions.
- Capability inventory: Writing files to the repository (
sdlc/<work-item>/intent.md) and invoking interactive user questioning tools. - Sanitization: No input validation or sanitization is performed on the incoming request before it is processed into the intent document.
Audit Metadata