research-methods-router

Pass

Audited by Gen Agent Trust Hub on Aug 25, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-provided research parameters (such as study type and population) directly into the search queries for other capabilities.
  • Ingestion points: User-provided study type, population, and evidence scope (SKILL.md).
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to ignore potentially malicious content within the user-supplied parameters.
  • Capability inventory: The skill utilizes skill_search for discovery and skill_load for execution of external research methodologies.
  • Sanitization: There is no mention of input validation or escaping for the data interpolated into the skill routing tools.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 25, 2026, 02:12 AM
Security Audit — agent-trust-hub — research-methods-router