uno-reverse
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of instructional markdown and a template for a subagent tool call. It does not contain any executable code, external dependencies, or network operations outside of references to the author's own domain.
- [PROMPT_INJECTION]: The skill includes directives for a subagent to ignore previous conversational context ('ZERO investment in prior discussions'). While this matches patterns for instruction overrides, it is a functional design choice to prevent confirmation bias during technical audits, which is the stated primary purpose of the skill. In this context, the pattern is assessed as safe.
- [NO_CODE]: The skill does not bundle any scripts, binaries, or automated installation procedures, limiting its execution to natural language reasoning and standard tool invocations.
Audit Metadata