sales-call-prep
Pass
Audited by Gen Agent Trust Hub on Apr 10, 2026
Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill is designed to ingest and process highly sensitive business data, including CRM records (Salesforce, HubSpot), communication history (Outreach, email), and personal professional profiles. While this is core to its function, the aggregation of this data into the model context creates a high-sensitivity environment.
- [PROMPT_INJECTION]: The skill is vulnerable to Indirect Prompt Injection (Category 8) because it searches for and processes untrusted data from the web, such as LinkedIn posts, social media comments, and product reviews. This content could contain malicious instructions designed to manipulate the agent's analysis or output.
- Ingestion points: Web search results, LinkedIn profiles, social media posts, and product reviews (Step 2 and Step 3).
- Boundary markers: None explicitly defined in the instructions to prevent the agent from following instructions embedded in the researched content.
- Capability inventory: The skill generates complex reports and strategies which could be influenced by injected content.
- Sanitization: No specific sanitization or validation of external content is mentioned.
Audit Metadata