account-research

Pass

Audited by Gen Agent Trust Hub on Apr 7, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill's instructions and execution flow align with its stated purpose of providing company and person research. It uses standard business data points and search queries.\n- [SAFE]: No evidence of hardcoded credentials, malicious obfuscation, or unauthorized network operations was found.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it processes untrusted data from web searches and external sources (Step 2 and 3). However, this is the primary intended function of a research skill. Ingestion points: Web search results and enrichment/CRM data in SKILL.md. Boundary markers: None present. Capability inventory: Web search and API data retrieval. Sanitization: None specified in instructions. Given this is the primary purpose and no malicious intent is visible, the finding is categorized as safe.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 7, 2026, 03:21 PM
Security Audit — agent-trust-hub — account-research