employee-handbook-builder

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted external data in the form of existing employee handbooks or policy documents.
  • Ingestion points: Processes user-provided "outdated handbook or scattered policy docs" during the modernization workflow in SKILL.md.
  • Boundary markers: There are no explicit instructions, delimiters, or warning prompts defined to isolate the untrusted input from the agent's core instructions.
  • Capability inventory: The agent has access to Bash, Write, Read, and WebSearch tools.
  • Sanitization: No sanitization, filtering, or validation of the ingested document content is specified before the agent processes the text.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 06:05 PM
Security Audit — agent-trust-hub — employee-handbook-builder