prompt-synthesis

Pass

Audited by Gen Agent Trust Hub on Aug 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill explicitly defines hard bounds for the agent, mandating the use of read-only tools and prohibiting any operations that involve writing, editing, deleting, shell-mutation, or code execution.
  • [SAFE]: It employs a structured output schema and anti-fluff instructions that prevent the agent from including unnecessary narration, tool dumps, or metadata that could be used for prompt injection or instruction override.
  • [SAFE]: Data ingestion is limited to local workspace guideline files and user input for grounding, with specific instructions to avoid inventing information or filling gaps with assumptions.
  • [SAFE]: The skill does not contain any hardcoded credentials, obfuscated content, or references to external, untrusted code sources.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 18, 2026, 12:28 PM
Security Audit — agent-trust-hub — prompt-synthesis