sales-call-prep
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection as it processes untrusted data from multiple external sources.
- Ingestion points: Reads outreach replies, CRM interaction notes, LinkedIn activity, and web search results to build the intelligence brief (SKILL.md).
- Boundary markers: Absent; the instructions do not include delimiters or specific guidance for the agent to ignore instructions that might be embedded within the researched content.
- Capability inventory: The skill utilizes
web-search,contact-finding, anddata-analysistools. - Sanitization: Absent; the skill summarizes and interpolates raw external data directly into the final call strategy and talking points without validation.
Audit Metadata