ib-pitch-book

Pass

Audited by Gen Agent Trust Hub on May 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security threats or malicious patterns were identified in the skill instructions, reference files, or HTML templates.
  • [PROMPT_INJECTION]: The skill processes untrusted external data (filings, scraped pages, PDFs) but implements defenses against indirect prompt injection. (1) Ingestion points: External filings and documents (SKILL.md). (2) Boundary markers: Instructs agent to treat all external sources as untrusted evidence (SKILL.md). (3) Capability inventory: No dangerous commands in the skill code. (4) Sanitization: Explicit instructions to ignore embedded commands (compliance.md).
  • [DATA_EXFILTRATION]: No exfiltration patterns or hardcoded credentials found; the workflow includes specific rules for protecting sensitive management-provided data (MNPI).
  • [EXTERNAL_DOWNLOADS]: Mentions external workflow sources from a trusted organization for attribution purposes, which does not pose a security risk.
Audit Metadata
Risk Level
SAFE
Analyzed
May 8, 2026, 09:54 AM