adding-tests
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists of markdown documentation guiding an agent on testing strategies; it contains no executable code or scripts.
- [PROMPT_INJECTION]: The skill instructs the agent to read external bug reports via the
ghCLI. This constitutes an indirect prompt injection surface where untrusted data could influence agent behavior. - Ingestion points: GitHub issue content read via the
ghtool (branches/bug-fix.md). - Boundary markers: Absent; there are no instructions to wrap or delimit external content to prevent instruction override.
- Capability inventory: The agent is expected to generate code and potentially execute commands based on these external reports.
- Sanitization: No sanitization or validation of issue content is described in the guidelines.
- [SAFE]: Recommendations for using temporary directories and test guards for configuration isolation are documented as best practices, which enhances the security and reliability of the testing environment.
Audit Metadata