ai-regression-testing

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands such as 'bun test' and 'bun run typecheck' to verify test outcomes and code correctness within the user's project environment.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it incorporates external data like bug reports and code diffs into its decision-making process for writing and running tests.
  • Ingestion points: Processes external bug reports and code diffs as primary inputs for test generation (SKILL.md).
  • Boundary markers: Lacks explicit delimiters or instructions for separating external input from internal task logic.
  • Capability inventory: The agent can modify local files and execute shell commands based on the context of the testing task (SKILL.md).
  • Sanitization: No visible mechanisms for sanitizing or escaping the content of processed diffs or reports are specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 01:13 PM
Security Audit — agent-trust-hub — ai-regression-testing