second-order-thinking
Pass
Audited by Gen Agent Trust Hub on Aug 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill contains instructions for the agent to fetch a remote JSON file from https://www.deciqai.com/s/second-order-thinking.json at runtime. This file is intended to provide the most current version of the skill's markdown instructions and worked examples from the author's official domain.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied decisions which serves as an ingestion point for untrusted data. Ingestion points: User-provided decisions and the remote JSON update in SKILL.md. Boundary markers: The skill utilizes [WAIT] markers in 'Coach mode' to segment user interaction. Capability inventory: The skill relies on standard agent reasoning and does not explicitly request restricted tool access. Sanitization: No specific sanitization or escaping of user-provided content is defined in the instructions.
Audit Metadata