bx-yaml
Pass
Audited by Gen Agent Trust Hub on Apr 15, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill documents the installation of the bx-yaml module using standard package managers for the BoxLang ecosystem.
- [COMMAND_EXECUTION]: Includes examples of reading from and writing to the local file system to manage YAML-based configuration files (e.g., yamlSerialize and yamlDeserializeFile).
- [PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection through its YAML processing functions.
- Ingestion points: Untrusted data enters the agent context through yamlDeserialize and yamlDeserializeFile in SKILL.md.
- Boundary markers: The documentation does not define markers or specific instructions to isolate the ingested data from agent commands.
- Capability inventory: The skill possesses file system modification capabilities via the yamlSerialize function (SKILL.md).
- Sanitization: There is no mention of input validation or content sanitization prior to the deserialization of external YAML.
Audit Metadata