tree-of-thought

Pass

Audited by Gen Agent Trust Hub on May 12, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill consists exclusively of natural language instructions guiding the agent through decomposition, solution generation, evaluation, and synthesis phases.
  • [SAFE]: User input is incorporated via the $ARGUMENTS placeholder. While no explicit boundary markers are present to wrap this input, the skill lacks access to any dangerous tools or system capabilities, mitigating the risk of indirect prompt injection.
  • [SAFE]: No external downloads, package dependencies, or dynamic code execution patterns are present in the skill files or metadata.
  • [SAFE]: The installation instructions in the README refer to the author's own GitHub repository and standard tool-specific commands, representing expected distribution behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
May 12, 2026, 09:09 PM