competitive-intelligence

Pass

Audited by Gen Agent Trust Hub on Feb 19, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [Indirect Prompt Injection] (LOW): The skill documentation defines a mechanism where external files are loaded as content to guide agent behavior, creating a potential surface for injection. * Ingestion points: context/role.md, context/company.md. * Boundary markers: Absent (documentation specifies files are loaded as content). * Capability inventory: None (no scripts or executable code provided in the skill files). * Sanitization: Absent (no validation or escaping of ingested data is described).
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 19, 2026, 03:54 PM