writing-beats
Pass
Audited by Gen Agent Trust Hub on Jun 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is designed for interactive writing and does not contain any malicious patterns such as data exfiltration, unauthorized network requests, or credential theft. All file operations are consistent with the stated purpose of article management.- [PROMPT_INJECTION]: The skill possesses a data ingestion surface for indirect prompt injection, as it processes 'raw material' and reads back the generated article from disk.
- Ingestion points: The agent reads from a markdown file containing raw notes and an article file stored on the local disk.
- Boundary markers: There are no specific delimiters or instructional barriers defined to separate the untrusted input data from the agent's logic.
- Capability inventory: The skill has the ability to read and write files on the local filesystem.
- Sanitization: The instructions do not specify any validation or sanitization procedures for the input material.
Audit Metadata