sdd-review
Pass
Audited by Gen Agent Trust Hub on Apr 29, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes content from external project files and source code.
- Ingestion points: Reads docs/project.md, feature.md, plan.md, and codebase files identified via git.
- Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external file content as untrusted data or to ignore embedded instructions.
- Capability inventory: Generates detailed reports and suggests code fixes based on analyzed files; utilizes shell commands for file discovery.
- Sanitization: No input validation or content filtering is implemented for the ingested data.
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to resolve the scope of the code review.
- Evidence: git diff main...HEAD --name-only (SKILL.md).
Audit Metadata