deal-screening

Pass

Audited by Gen Agent Trust Hub on May 1, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill consists entirely of markdown instructions and templates for analyzing business documents. No executable scripts, binaries, or configuration files are included.\n- [NO_CODE]: No code or external dependencies were detected in the skill contents.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes external Confidential Information Memorandums (CIMs), which creates a theoretical attack surface for indirect prompt injection. However, the skill lacks dangerous capabilities such as network access or shell execution, neutralizing the risk.\n
  • Ingestion points: Processes target CIMs and buyer memos as described in SKILL.md.\n
  • Boundary markers: Absent; no explicit delimiters or instructions to ignore embedded commands are present in the extraction protocol.\n
  • Capability inventory: None detected; the skill does not use shell commands, network tools, or file system writes.\n
  • Sanitization: Absent; no validation or sanitization of input document content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 1, 2026, 10:50 PM