skills/xindoo/sumeru/sumeru-topic/Gen Agent Trust Hub

sumeru-topic

Pass

Audited by Gen Agent Trust Hub on May 5, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates entirely within the scope of creative writing assistance. It performs AI-based reasoning to generate novel themes and evaluations without requesting external data or executing untrusted code.
  • [DATA_EXFILTRATION]: No network operations (e.g., curl, wget, or API calls) are present. The skill does not access sensitive system paths, credentials, or environment variables.
  • [COMMAND_EXECUTION]: The skill does not invoke shell commands, sub-processes, or dynamic code execution (eval/exec).
  • [PROMPT_INJECTION]: The instructions are clear and purpose-oriented. There are no attempts to override agent behavior, extract system prompts, or bypass safety guidelines.
  • [SAFE]: File operations are limited to writing generated reports and structured JSON data to the local project directory and a specific internal subdirectory (.sumeru/topic/) for persistence. This is standard behavior for document-generation skills.
Audit Metadata
Risk Level
SAFE
Analyzed
May 5, 2026, 06:33 AM
Security Audit — agent-trust-hub — sumeru-topic