auto-research

Pass

Audited by Gen Agent Trust Hub on Aug 17, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill features an inherent surface for indirect prompt injection because its core function involves ingesting and analyzing data from untrusted external sources.
  • Ingestion points: The workflow relies on intelli_research, web_fetch, and file reading tools to acquire data from the web and local files.
  • Boundary markers: The instructions do not mandate the use of delimiters to isolate retrieved content from the agent's logic, which is common in research-oriented skills.
  • Capability inventory: Capabilities include web searching, URL fetching, and reading local files or cloned repositories.
  • Sanitization: No specific filtering or escaping of retrieved content is requested in the research templates.
  • [SAFE]: The skill uses established tools for its stated purpose, lacks obfuscation, and does not contain hardcoded credentials or unauthorized data exfiltration patterns.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 17, 2026, 11:53 AM
Security Audit — agent-trust-hub — auto-research