exposure-risk-quantification

Pass

Audited by Gen Agent Trust Hub on Aug 14, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external reconnaissance findings, which creates a surface where malicious instructions could be embedded in the data being quantified.
  • Ingestion points: Processes findings, assets, and metadata collected during reconnaissance passes (documented in SKILL.md §1 and §7).
  • Boundary markers: The instructions lack explicit delimiters or guidance for the agent to distinguish between findings data and control instructions, increasing the risk of the agent obeying instructions embedded within processed assets.
  • Capability inventory: The skill possesses the capability to curate data, perform complex mathematical calculations, and trigger report rendering (mentioning headless Chromium and Playwright in §10.5).
  • Sanitization: There is no mention of sanitization, escaping, or schema validation to ensure that external content is safe before it is interpolated into quantification routines or reports.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 14, 2026, 11:31 AM
Security Audit — agent-trust-hub — exposure-risk-quantification