doc-specialist

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes scraped documentation to generate agent instructions, which creates a surface for indirect prompt injection.
  • Ingestion points: Documentation files (INDEX.md, FULL_DOCS.md) in the library folder specified by the user.
  • Boundary markers: None identified; documentation content is directly interpolated into the system prompt template without isolation markers.
  • Capability inventory: The generated agent is configured with powerful tools including Bash, Read, Grep, and WebFetch.
  • Sanitization: No sanitization or escaping of documentation content is performed before inclusion in the instructions.
  • [COMMAND_EXECUTION]: The skill requires the execution of a Python script (generate_specialist.py) to generate agent templates and configures those agents with the Bash tool, enabling the execution of shell commands on the host system.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 12:37 PM
Security Audit — agent-trust-hub — doc-specialist