cohort-coach

Warn

Audited by Gen Agent Trust Hub on Sep 25, 2026

Risk Level: MEDIUMMETADATA_POISONINGSAFE
Full Analysis
  • [SAFE]: The skill body consists of natural language instructions and examples for facilitating cohort-based learning. It does not include any executable scripts, binary files, or system command patterns.
  • [SAFE]: No external network operations, data exfiltration patterns, or sensitive file access attempts were identified.
  • [METADATA_POISONING]: The author field in the YAML frontmatter is set to 'Claude Code'. 'Claude Code' is the official name of the CLI agent developed by Anthropic. Using this name is misleading regarding the skill's origin, as the footer indicates it is part of a third-party collection hosted by 'inbharatai'.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 25, 2026, 10:37 PM