prospect-research-compiler
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process information from untrusted external sources, including news, social media, company websites, and financial data. This creates a surface for indirect prompt injection where malicious instructions hidden in a prospect's public profile or a news article could influence the agent's behavior.
- Ingestion points: External sources such as news, social media, company websites, and financial data mentioned in the description and instructions (SKILL.md).
- Boundary markers: Absent. The instructions do not provide specific delimiters or warnings to the agent to disregard instructions found within the gathered intelligence.
- Capability inventory: The skill facilitates the aggregation and formatting of external data into prospect profiles; while no custom scripts are present, the agent uses its core capabilities to browse and summarize this content.
- Sanitization: Absent. There are no instructions for the agent to filter or sanitize the content retrieved from external sources before including it in the final output.
Audit Metadata