skills/liangmiqwq/skills/adding-tests/Gen Agent Trust Hub

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 gh CLI. This constitutes an indirect prompt injection surface where untrusted data could influence agent behavior.
  • Ingestion points: GitHub issue content read via the gh tool (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
Risk Level
SAFE
Analyzed
Jun 23, 2026, 03:14 AM
Security Audit — agent-trust-hub — adding-tests