agently-prompt-config-files
Pass
Audited by Gen Agent Trust Hub on Mar 11, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [NO_CODE]: This skill consists entirely of documentation and reference files with no executable scripts or malicious code.
- [SAFE]: The content describes official features of the Agently framework (version >= 4.0.8.5) and adheres to safe practices like using yaml.safe_load.
- [EXTERNAL_DOWNLOADS]: External references point to official Agently repositories on GitHub and the agently.tech documentation site, which are trusted vendor resources.
- [COMMAND_EXECUTION]: The documented .alias feature is a framework-internal configuration mechanism for agent method invocation and does not facilitate arbitrary shell command execution.
- [DATA_EXFILTRATION]: File loading and saving behaviors are restricted to prompt configuration management with no access to sensitive system paths or unauthorized network communication.
- [SAFE]: [Indirect Prompt Injection Surface] Ingestion points: load_yaml_prompt and load_json_prompt (loading-mappings-and-key-paths.md). Boundary markers: Absent. Capability inventory: Agent method execution via .alias (alias-and-roundtrip.md). Sanitization: yaml.safe_load (loading-mappings-and-key-paths.md). This documentation describes standard framework functionality from a trusted author.
Audit Metadata