source-quality-appraiser

Pass

Audited by Gen Agent Trust Hub on Jul 12, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and analyze untrusted data from external research papers to evaluate methodological strength. Ingestion points: External paper text and metadata processed during quality appraisal in SKILL.md. Boundary markers: None specified. Capability inventory: Scientific reasoning and external database queries; no system-level execution or file system write capabilities detected. Sanitization: None mentioned.
  • [EXTERNAL_DOWNLOADS]: The skill references established academic resources for validation. It fetches accreditation data from the official SINTA Kemdikbud portal and utilizes OpenAlex for global journal metrics and indexation fallback.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 12, 2026, 11:44 AM
Security Audit — agent-trust-hub — source-quality-appraiser