executive-orchestration

Pass

Audited by Gen Agent Trust Hub on Oct 24, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external data sources to inform executive decisions.\n
  • Ingestion points: It reads 'reliable company context' (including business models and priorities) and 'durable company/project records' from the environment (SKILL.md).\n
  • Boundary markers: The instructions do not specify technical markers or 'ignore embedded instructions' warnings to isolate external data from the system prompt.\n
  • Capability inventory: The skill acknowledges the agent's ability to 'execute actions' and make 'spending commitments' if authorized by tool permissions (SKILL.md).\n
  • Sanitization: No explicit sanitization or validation of the retrieved company records is defined in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 24, 2026, 04:13 PM