negative-contrastive-framing
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is composed of purely descriptive and instructional content designed to guide the agent in a specific cognitive task. All provided files (SKILL.md, methodology.md, rubric, and template) are text-based and contain no executable logic.
- [NO_CODE]: The skill does not contain or reference any source code (Python, JavaScript, etc.) or external software dependencies. All logic is contained within natural language instructions and structured markdown templates.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-provided definitions. While this presents a standard input surface for data ingestion, the skill lacks any dangerous capabilities such as shell access, sensitive file writes, or network requests that could be exploited via malicious input.
Audit Metadata