sdd-draft-proposal
Pass
Audited by Gen Agent Trust Hub on Jul 12, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill includes hard rules that enforce a 'plan-only' workflow, explicitly prohibiting state-changing commands, code edits, builds, or installations.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill restricts itself to read-only access of the codebase for discovery purposes and requires explicit user consent before performing its single permitted write operation.- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from the repository and user interview to generate drafts.
- Ingestion points: User interview input and repository documentation (SKILL.md).
- Boundary markers: None present in the template.
- Capability inventory: Writing Markdown files after user approval (SKILL.md).
- Sanitization: No specific sanitization or filtering logic is defined for the ingested data.
Audit Metadata