triage

Pass

Audited by Gen Agent Trust Hub on Jul 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it instructs subagents to read and verify findings based on untrusted external artifacts.
  • Ingestion points: Findings (id and claim) and artifact paths provided by the caller are processed directly (SKILL.md).
  • Boundary markers: The instructions do not define delimiters or specific warnings to ignore embedded instructions within the findings or artifacts.
  • Capability inventory: Subagents are tasked with reading artifacts and judging findings, which involves processing potentially malicious content (SKILL.md).
  • Sanitization: There is no evidence of sanitization or validation of the input data before it is passed to subagents.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 24, 2026, 12:12 PM
Security Audit — agent-trust-hub — triage