domain-dns-configurator
Pass
Audited by Gen Agent Trust Hub on Jul 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill's documentation contains a validation section with shell commands that invoke Python scripts from the local
$CODEX_HOMEenvironment. These appear to be internal platform tools used for linting and schema validation during the development process and do not represent a runtime security risk. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and inventory existing DNS records, which could potentially contain malicious instructions (e.g., in TXT records). However, the skill is strictly limited to planning and "dry-run" activities, with no capability to execute commands or modify the environment, which effectively neutralizes this attack vector.
- Ingestion points: DNS record inventory (SKILL.md, Workflow step 1)
- Boundary markers: Absent.
- Capability inventory: The skill does not define or request any tools for network operations, file system writes, or subprocess execution.
- Sanitization: Absent.
Audit Metadata