Ukhradviser

Pass

Audited by Gen Agent Trust Hub on Apr 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it is designed to ingest and process untrusted user context regarding workplace disputes and employment contracts to generate legal guidance.
  • Ingestion points: User-provided descriptions of HR issues, employment details, and contract terms are processed in SKILL.md.
  • Boundary markers: The skill does not implement explicit delimiters or instructions to treat user-provided text as untrusted data.
  • Capability inventory: The agent has the capability to perform web searches for current legislation and read local skill documentation files (CLAUDE.md) based on the ingested context, as specified in SKILL.md.
  • Sanitization: There are no defined procedures for the sanitization or validation of user input within the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 5, 2026, 07:42 AM