sales-account-intelligence
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security risks were found in the skill metadata or instructions.
- [NO_CODE]: The skill does not include any scripts or executable files.
- [PROMPT_INJECTION]: The skill defines a workflow that ingests external web data, creating a surface for indirect prompt injection.
- Ingestion points: The extract and crawl capabilities are used to pull content from external company websites and news sources.
- Boundary markers: There are no explicit instructions to the agent to disregard commands embedded in the retrieved web content.
- Capability inventory: The agent uses search and extraction tools to process external data.
- Sanitization: The skill does not specify sanitization or validation of retrieved web content before it is incorporated into the account brief.
Audit Metadata