qa-assistant

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill strictly adheres to a read-only principle, explicitly forbidding commands that would modify, move, or delete files.
  • [SAFE]: No evidence of prompt injection, data exfiltration, or obfuscation was detected in the skill's instructions or metadata.
  • [SAFE]: The skill relies on standard local search tools (read_file, grep_search, semantic_search) for data retrieval within the local project scope, which is the intended and safe use case.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 01:44 PM