skills/product-on-purpose/thinking-framework-skills/think-walton-argumentation-schemes/Gen Agent Trust Hub
think-walton-argumentation-schemes
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze user-supplied defeasible arguments. While this constitutes a surface for indirect prompt injection, the risk is neutralized by the skill's restricted capabilities, which are limited to text processing and generating markdown artifacts.
- Ingestion points: User-provided arguments are ingested for classification and evaluation as described in
SKILL.md. - Boundary markers: The instructions do not explicitly define delimiters for user input, though the process of restating the argument and filling premise slots provides a structured handling of the data.
- Capability inventory: No network operations, file system modifications, or shell command executions are performed by this skill.
- Sanitization: No formal input sanitization is present, as the skill operates entirely within the agent's text-processing context.
Audit Metadata