sales-expert

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill defines a specialized sales coaching persona and focuses on providing strategic advice based on well-known sales methodologies.- [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety filters, ignore prior instructions, or extract system prompts.- [EXTERNAL_DOWNLOADS]: The skill is configured with tools such as WebFetch and WebSearch to retrieve sales-related information. This activity is restricted to data retrieval and does not involve downloading or executing external scripts.- [DATA_EXFILTRATION]: The skill does not contain instructions to access sensitive files (e.g., credentials, SSH keys) or transmit user data to unauthorized external domains.- [SAFE]: Indirect Prompt Injection risk assessment: Ingestion points: WebFetch and mcp__scout__readable_text are used to process external content. Boundary markers: No explicit markers are defined. Capability inventory: The skill is restricted to reading and searching; it lacks write or execution capabilities. Sanitization: No sanitization logic is specified. Evaluation: The risk is negligible as the agent lacks the tools required to execute malicious instructions found in processed data.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:41 PM
Security Audit — agent-trust-hub — sales-expert