sales-call-script
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's core workflow requires the agent to conduct intensive research by accessing external sources, including LinkedIn profiles, company websites, and news articles, to identify rapport-building points.
- Ingestion points: Data is ingested from external web pages, social media, and news summaries as described in Workflow 1, Step 1.
- Boundary markers: There are no instructions providing delimiters or 'ignore' directives for the ingested external data to prevent the agent from following malicious instructions hidden in those sources.
- Capability inventory: The skill directs the agent to perform research and use the gathered information to generate sales pitches and responses, involving network/browsing capabilities.
- Sanitization: The instructions lack specific validation or sanitization steps for the data retrieved from external sources before it is processed by the AI.
Audit Metadata