sdlc-create-intent
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest informal software requests, bugs, or refactor requirements to generate structured intent artifacts. This creates an attack surface where malicious instructions embedded in a software request could influence the agent's behavior or the content of the resulting artifact.
- Ingestion points: Informal software requests processed as required input in the 'Inputs and output' section.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the input requests.
- Capability inventory: The skill performs file writes (creating
intent.md) and uses interactive tools (AskUserQuestion). - Sanitization: There is no explicit sanitization, validation, or filtering of the input request content before it is used to generate the output artifact.
- Note: The risk is categorized as low because the skill's primary function is documentation generation and the 'Handoff' section explicitly requires human review of the generated artifact before further action.
Audit Metadata