sales-performance-review
Pass
Audited by Gen Agent Trust Hub on Jul 20, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it ingests and evaluates data from external sales initiatives and CRM systems.
- Ingestion points: Untrusted data enters the agent context from outreach tools like Smartlead and Instantly, and CRM platforms like Hubspot or manual spreadsheets in Steps 1 and 2.
- Boundary markers: The instructions lack specific delimiters or directions to ignore embedded instructions within the gathered sales data.
- Capability inventory: The skill's primary functions are data analysis and report generation; it does not perform high-risk operations such as shell command execution or persistent file modification.
- Sanitization: There is no mention of sanitizing or escaping the external content before it is interpolated into the analysis prompts.
Audit Metadata