resonance-sales-lead-ops
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from an external CRM system.
- Ingestion points: The skill reads lead-related data including contact, company, and deal information, as well as conversation evidence like CRM notes and chat threads (SKILL.md).
- Boundary markers: There are no instructions for using boundary markers or delimiters to isolate ingested CRM data from the agent's system instructions.
- Capability inventory: The skill's documented capabilities are limited to data analysis and reporting; no high-risk tools such as shell execution, network requests, or file system writes are utilized.
- Sanitization: The procedure does not include steps for sanitizing, escaping, or validating the content retrieved from CRM records before it is processed by the agent.
Audit Metadata