specialist-engineering-agentic-identity-trust

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill defines a subagent template that ingests untrusted user data into its operational prompt, which is a common surface for indirect prompt injection.
  • Ingestion points: User input is interpolated via the {the user's question} placeholder within the Agent tool call in SKILL.md.
  • Boundary markers: The template does not utilize clear delimiters or specific instructions to ensure the agent distinguishes between its core directives and the provided user input.
  • Capability inventory: The skill invokes the Agent tool to spawn subagents, passing the potentially unvetted user input directly into the specialist agent's context.
  • Sanitization: There is no evidence of escaping, filtering, or validation of the input before it is used to construct the final prompt.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 08:49 PM
Security Audit — agent-trust-hub — specialist-engineering-agentic-identity-trust