zero-tech-debt
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the local filesystem through search and read operations.
- Ingestion points: The skill uses Read, Glob, Grep, Bash(rg:), and Bash(fd:) to import existing codebase content into the agent context, as described in references/03-workflow.md and references/04-audit-patterns.md.
- Boundary markers: The instructions do not define boundary markers or explicit instructions for the agent to ignore prompts that may be embedded in the source code files.
- Capability inventory: The skill is configured with Edit for file modifications and Bash(git:*) for repository operations, enabling it to perform structural changes to the project.
- Sanitization: There are no documented sanitization or filtering procedures for the content retrieved from the codebase before it is processed by the agent.
Audit Metadata