ns-sdd-task-generator
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a specialized documentation generator that processes local project requirements and architectural rules to produce task-NNN-slug.md files. It does not perform network requests or execute arbitrary system commands.- [SAFE]: No sensitive file paths (e.g., .ssh, .aws) are accessed, and no hardcoded credentials or obfuscated strings were found.- [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted project documentation from 'requirements.md'. However, this is considered safe in context as the agent's capabilities are limited to generating markdown documentation and it lacks access to dangerous tools. 1. Ingestion points: 'requirements.md' and rule files in the harness root. 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present. 3. Capability inventory: File-writing restricted to the documentation/tasks directory. 4. Sanitization: No input validation or content escaping is implemented.
Audit Metadata