account-qualification
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWNO_CODE
Full Analysis
- [NO_CODE] (SAFE): The file consists entirely of Markdown instructions and templates. No executable scripts (.py, .js, .sh), configuration files, or hidden payloads were detected.
- [EXTERNAL_DOWNLOADS] (SAFE): While the skill references external tools like Perplexity, Exa, and Apify, these are defined as Model Context Protocol (MCP) tools. The skill itself does not download or execute remote scripts; it instructs the agent on how to query these APIs if configured by the user.
- [INDIRECT_PROMPT_INJECTION] (LOW):
- Ingestion points: Data enters the system via external search tools (Perplexity/Exa) and web scraping (Apify).
- Boundary markers: None identified in the provided templates.
- Capability inventory: No write, execute, or network-send capabilities are present in this skill.
- Sanitization: No specific sanitization logic is present for external data.
- Assessment: Since the skill only performs classification and tiering (internal reasoning), the risk of indirect injection causing harm is negligible.
Audit Metadata