yagni
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructional guidelines for software development and does not contain malicious code, hidden commands, or credential exfiltration attempts.
- [COMMAND_EXECUTION]: The skill permits the use of standard development tools and version control commands, such as
git revertandgit restore, which are appropriate for its function as a coding assistant. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of user requirements and codebase content, creating a potential surface for indirect prompt injection.
- Ingestion points: The workflow requires the agent to read user requirements and project code files (SKILL.md).
- Boundary markers: Risk is mitigated by mandatory pre-execution plans that define explicit goals, non-goals, and acceptance criteria to ensure the agent stays within scope.
- Capability inventory: The agent can modify files, run tests, and execute version control commands (SKILL.md).
- Sanitization: There is no explicit mention of sanitizing or escaping the content read from external files or user input.
Audit Metadata