subtraction-thinking
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is composed of markdown instructions and reference templates. No executable code, remote script downloads, network requests, or sensitive file access patterns were identified in SKILL.md or references/tools.md.
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to process user-provided data for simplification analysis, which introduces a data ingestion surface.
- Ingestion points: User inputs described in SKILL.md (e.g., business decisions, service designs, and code snippets).
- Boundary markers: Absent; there are no specific instructions to use delimiters or ignore instructions within the processed data.
- Capability inventory: None; the skill does not utilize any scripts, subprocesses, network tools, or file-writing tools.
- Sanitization: Absent. The surface is considered safe because the skill lacks any capabilities that could be exploited via injection.
Audit Metadata