rt-workflow

Pass

Audited by Gen Agent Trust Hub on Aug 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [NO_CODE]: The analyzed file SKILL.md contains only markdown documentation and instructions. There are no executable scripts, shell commands, or configuration files that define active tools or capabilities.
  • [SAFE]: The skill is a high-level workflow router. Comprehensive analysis across all threat categories—including obfuscation, remote code execution, and privilege escalation—revealed no malicious patterns or safety concerns.
  • [INDIRECT_PROMPT_INJECTION]: \n
  • Ingestion points: The skill refers to paper-profile.yml (via ../../../shared-resources/journal-selection/paper-profile.md) as a consolidated source for manuscript signals.\n
  • Boundary markers: Not defined in this router skill; boundary management is deferred to the specialized sub-skills it references.\n
  • Capability inventory: This skill possesses no active capabilities, such as file system writes, network access, or command execution.\n
  • Sanitization: Not applicable as this skill does not process the data, only directs the agent to other tools that do.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 24, 2026, 10:29 AM
Security Audit — agent-trust-hub — rt-workflow