sec-em7-expense-acceleration

Pass

Audited by Gen Agent Trust Hub on Feb 18, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [No Code] (SAFE): The skill is entirely composed of markdown instructions and metadata. It does not include scripts, binaries, or system commands.
  • [Indirect Prompt Injection] (LOW): The skill instructions create a surface for processing untrusted external data. 1. Ingestion points: Financial data including restructuring charges, peer norms, and inventory write-downs (SKILL.md). 2. Boundary markers: None defined. 3. Capability inventory: None; the skill does not possess file-writing, network access, or command execution capabilities. 4. Sanitization: Not specified in the skill content.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 18, 2026, 09:15 AM