research-evidence-archive

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill establishes a robust knowledge management structure for research data. It explicitly defines redaction rules in references/archive-layout.md to prevent the storage of sensitive information such as account credentials, session cookies, and private brokerage details.
  • [SAFE]: The skill includes a 'Quality Gate' in SKILL.md requiring verification that no secrets or private data were stored, demonstrating a proactive security posture for local data persistence.
  • [SAFE]: The skill exhibits an indirect prompt injection surface through the ingestion of external research materials (filings, news, media) into the repository at research/evidence/. However, risk is mitigated by explicit requirements in SKILL.md to maintain clear boundaries between raw sources and synthesized analysis, coupled with redaction policies for sensitive information. Capability is limited to file organization within the designated research directory.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 10:23 PM
Security Audit — agent-trust-hub — research-evidence-archive