one-three-one-rule
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is entirely instructional and provides a template for the '1-3-1' rule of communication. It does not execute any commands, write files, or perform network requests.- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data during technical analysis. 1. Ingestion points: User-provided descriptions of technical problems or choice scenarios in SKILL.md. 2. Boundary markers: No explicit delimiters or 'ignore' instructions are defined for the user input. 3. Capability inventory: No subprocess, file, or network capabilities are present in the skill files. 4. Sanitization: No sanitization is performed on user content. This is a low-risk surface as the skill possesses no exploitable capabilities.
Audit Metadata