lead
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
gitand a task-tracking utility namedbdfor repository and workflow management. - [PROMPT_INJECTION]: The skill exposes a surface for indirect prompt injection as it processes repository files to provide context for sub-agents.
- Ingestion points: Reads local project files and directory structures to populate teammate spawn prompts (SKILL.md).
- Boundary markers: No specific delimiters or safety instructions are prescribed for the passed context.
- Capability inventory: Can spawn agents, run quality gates, and modify repository state.
- Sanitization: No content validation or sanitization is mentioned.
Audit Metadata