skill-workflow-orchestrator

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
  • [NO_CODE]: The skill is entirely composed of documentation and guidelines in the SKILL.md file; it contains no script files, binaries, or other executable code.
  • [PROMPT_INJECTION]: The skill acts as a workflow orchestrator that processes natural language input and data from sub-skills to determine execution steps, which presents a surface for indirect prompt injection. * Ingestion points: Natural language task descriptions from users and data processed by tools like the 'pdf' reader (SKILL.md). * Boundary markers: No delimiters or guidelines are defined to separate user instructions from data being processed (SKILL.md). * Capability inventory: The skill can trigger operations such as web searches, file reading, and sending emails (SKILL.md). * Sanitization: No sanitization or validation of untrusted data is mentioned before it is passed between tools (SKILL.md).
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 02:03 PM
Security Audit — agent-trust-hub — skill-workflow-orchestrator