feedback-coach

Pass

Audited by Gen Agent Trust Hub on Mar 11, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscated content, hardcoded credentials, or unauthorized network activity were detected. The skill consists of professional guidance and educational frameworks.
  • [NO_CODE]: The skill does not include any executable scripts, packages, or binary files.
  • [PROMPT_INJECTION]: The skill defines a workflow for processing user-provided feedback scenarios, which represents an indirect prompt injection surface.
  • Ingestion points: User-provided feedback and context during coaching interactions (SKILL.md).
  • Boundary markers: Not specified.
  • Capability inventory: None; the skill lacks access to the shell, file system, or external network.
  • Sanitization: Not specified. The risk of exploitation is negligible given the complete lack of dangerous capabilities.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 11, 2026, 01:27 AM