aris-research-wiki

Pass

Audited by Gen Agent Trust Hub on May 6, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection through the ingestion of external research paper metadata.
  • Ingestion points: External research data is fetched from sources like arXiv, DBLP, and Semantic Scholar and stored in the 'papers/' directory.
  • Boundary markers: The skill uses YAML and Markdown headers for structure, but lacks explicit instructions to treat the ingested data as untrusted or to ignore instructions within that data.
  • Capability inventory: The skill utilizes powerful tools including Bash(*), Write, Edit, and Agent interaction, which could be leveraged if an injected prompt is successfully executed.
  • Sanitization: There is no mention of sanitization or filtering of the content retrieved from external research databases.
  • [EXTERNAL_DOWNLOADS]: The skill fetches research paper metadata from well-known technology services including arXiv, DBLP, and Semantic Scholar to populate the knowledge base.
Audit Metadata
Risk Level
SAFE
Analyzed
May 6, 2026, 01:42 AM
Security Audit — agent-trust-hub — aris-research-wiki