thinking-framework
Pass
Audited by Gen Agent Trust Hub on Mar 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements a robust multi-agent orchestration framework for systematic thinking, utilizing specialized agents for problem definition, methodology execution, and strategic synthesis.
- [SAFE]: Analysis of all 27 files reveals no evidence of data exfiltration, hardcoded credentials, or malicious obfuscation. All external references are limited to the author's trusted repository.
- [PROMPT_INJECTION]: The skill processes external user input as 'problem statements' which are then interpolated into sub-agent prompts. While this constitutes an indirect prompt injection surface, the risk is minimal as the agent's capabilities are restricted to reasoning and the use of specialized logic-based MCP tools.
- [COMMAND_EXECUTION]: The README provides installation instructions using a vendor-specific CLI tool (prpm). This is a documented deployment procedure and does not involve runtime execution of arbitrary shell commands by the agent.
Audit Metadata