elite-qa

Pass

Audited by Gen Agent Trust Hub on Apr 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data exfiltration were detected. The skill is designed for manual testing assistance and operates as intended.
  • [COMMAND_EXECUTION]: The skill uses git and gh CLI tools to gather information about changes in the repository. These commands are standard for the skill's purpose of identifying user-facing changes for QA.
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection because it processes untrusted code diffs and file contents.
  • Ingestion points: Phase 1 (Step 1 & 2) in SKILL.md fetches diffs and reads changed files.
  • Boundary markers: No specific delimiters are used to wrap the ingested code content.
  • Capability inventory: The skill has the ability to read repository files and write markdown reports to the local file system.
  • Sanitization: No content sanitization or escaping is performed on the ingested code before it is analyzed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 13, 2026, 03:47 AM
Security Audit — agent-trust-hub — elite-qa