skills/product-on-purpose/thinking-framework-skills/think-interest-based-negotiation/Gen Agent Trust Hub
think-interest-based-negotiation
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests user-provided data about negotiation scenarios (deal descriptions, parties, and interests) to generate a preparation map. While this is an ingestion surface for untrusted data, the skill does not possess any risky capabilities like network access, file system writes, or command execution that could be exploited by such data.
- Ingestion points: User-provided negotiation details in SKILL.md.
- Boundary markers: The skill uses a structured Markdown template for output but does not explicitly define input delimiters.
- Capability inventory: No scripts, network tools, or file-writing operations are included or invoked.
- Sanitization: No explicit sanitization or filtering is defined for the input data.
- [NO_CODE]: The skill is composed entirely of Markdown instructions and YAML metadata. It does not include any Python scripts, Node.js packages, shell commands, or other executable components.
Audit Metadata