toml-python
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates reading external TOML configuration files, which represents an ingestion surface for potential indirect prompt injection if the files contain instructions directed at the agent.
- Ingestion points: Configuration files are parsed using
tomlkit.loadandTOMLFile.read()as shown inSKILL.md. - Boundary markers: The examples do not implement delimiters or safety instructions to prevent the agent from following directions embedded in configuration data.
- Capability inventory: The skill uses capabilities for file writing (
open("w")), directory creation (path.parent.mkdir), and atomic file replacement (shutil.move). - Sanitization: No sanitization or content validation is provided for the parsed TOML data beyond standard syntax checks.
- [SAFE]: The skill uses well-known Python libraries for its core functionality and does not include any malicious commands, unauthorized network access, or credential harvesting patterns. The behaviors described are entirely consistent with the primary purpose of managing application configuration.
Audit Metadata