sales-pro
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user-supplied data, such as product descriptions and customer profiles, to populate its sales frameworks.
- Ingestion points: Data entry occurs in 'Step 1: รวบรวม context' within SKILL.md, where users provide business-specific information.
- Boundary markers: The skill lacks explicit delimiters or specialized instructions to prevent the agent from following instructions that might be embedded within the user's business data.
- Capability inventory: The skill primarily involves text generation and formatting into Markdown files; it does not perform network operations or execute shell commands across the analyzed files.
- Sanitization: There is no evidence of input validation or sanitization to filter out potential injection patterns from the business context provided by the user.
Audit Metadata