list-builder

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: Indirect Prompt Injection Surface:
  • Ingestion points: External data enrichment fields such as company bios, strategic insights, and prospect profile data retrieved during the discovery and enrichment phases (SKILL.md).
  • Boundary markers: The skill logic does not specify the use of delimiters or 'ignore embedded instructions' warnings when handling data fetched from external sources.
  • Capability inventory: The skill has capabilities to perform network-based data retrieval (via vendor API) and write files (CSV artifacts).
  • Sanitization: There are no instructions for sanitizing or escaping the content retrieved from external sources before it is interpolated into the agent's context or output as a table artifact.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 04:10 PM
Security Audit — agent-trust-hub — list-builder