negative-news-triage

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it is designed to ingest and analyze untrusted data from news reports and vendor exports.
  • Ingestion points: Untrusted hit sets from external vendors and open-source exports (documented in SKILL.md).
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions when reading the raw hit content.
  • Capability inventory: The skill produces structured triage records and memos that are consumed by downstream agent skills like edd-escalation-pack and sar-decision-qa (documented in SKILL.md and templates/default-output.md).
  • Sanitization: The instructions do not specify any validation or sanitization procedures for the external hit content prior to processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 10:30 PM
Security Audit — agent-trust-hub — negative-news-triage