sdlc-create-spec
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a set of instructions for document generation within a software development lifecycle. It does not contain any executable scripts, shell commands, or network requests.- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data from files like
intent.mdand repository instructions. - Ingestion points: Reads
intent.mdand repository-level instruction files. - Boundary markers: None explicitly defined beyond standard file boundaries.
- Capability inventory: No system-writing, network, or code execution capabilities are defined or requested.
- Sanitization: None specified, but the output is restricted to markdown text formatting.
- Assessment: The lack of dangerous capabilities makes the injection surface negligible.
Audit Metadata