no-deferred-work
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill defines a set of best practices for software development aimed at reducing technical debt. All instructions and examples are consistent with standard professional engineering workflows.
- [COMMAND_EXECUTION]: The skill contains examples for using the GitHub CLI (gh) to create issues and Bash scripts for Git pre-commit hooks. These are provided as templates for the agent to follow and do not involve unauthorized or hidden command execution.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface where the agent processes code and interacts with external tools. Ingestion points: Local source code files and project status. Boundary markers: Absent. Capability inventory: GitHub CLI (gh) for issue creation and Git for development hooks. Sanitization: Absent. Conclusion: The vulnerability surface is standard for an AI development agent, and the skill does not introduce malicious logic.
Audit Metadata