to-narration
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is entirely instruction-based, defining a workflow for processing text from one file to another without requesting any sensitive permissions or tool access.
- [NO_CODE]: No external scripts, Python packages, or Node.js dependencies are referenced or included in the skill definition. The logic is handled purely by the agent's language processing capabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from an external file (
BEATS.md). While this constitutes an attack surface for indirect prompt injection, the skill lacks the necessary capabilities (such as network access, system command execution, or file system modification outside of the current project) to be leveraged for malicious purposes. The output is confined to a markdown document.
Audit Metadata