malloy-notebooks

Pass

Audited by Gen Agent Trust Hub on Aug 2, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill contains standard instructional language for generating Malloy notebooks. No bypass markers, role-play injections, or instructions to ignore safety guidelines were found.
  • [DATA_EXFILTRATION]: No network-capable commands or sensitive file path access were identified. Data source references point to local CSV and Parquet files within a standard data directory.
  • [REMOTE_CODE_EXECUTION]: The skill does not include any commands for remote script downloading or execution. It operates entirely within the context of generating Malloy and Markdown code for notebook files.
  • [COMMAND_EXECUTION]: There are no instances of shell command execution, privilege escalation, or persistence mechanism establishment.
  • [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or private keys were detected in the skill content.
  • [SAFE]: The skill functionality and behavior align with its stated purpose of assisting with Malloy notebook creation, with no evidence of malicious intent or deceptive practices.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 2, 2026, 09:02 AM
Security Audit — agent-trust-hub — malloy-notebooks