lead-research-assistant
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions direct the agent to analyze external data sources and local codebases to identify and qualify leads, which presents a surface for indirect prompt injection.
- Ingestion points: The skill ingests data from the local repository/codebase to understand the product (SKILL.md) and searches for external company information, including signals from target companies' GitHub repositories and websites (Instructions Step 3).
- Boundary markers: There are no instructions provided to use delimiters or ignore embedded commands within the files or web content being analyzed.
- Capability inventory: The skill possesses capabilities for local file reading (codebase analysis), network operations (searching for companies and signals), and file writing (suggesting CSV export of results).
- Sanitization: The instructions do not mention any sanitization, filtering, or escaping of the external content before it is processed or included in the final output.
Audit Metadata