writing-beats
Pass
Audited by Gen Agent Trust Hub on Sep 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted content from user-provided markdown files and article files stored on disk, using this content to generate suggestions and write to files.\n
- Ingestion points: The agent reads a 'markdown file of raw material' and 're-reads the article file from disk' to determine the next steps in the writing process (SKILL.md).\n
- Boundary markers: The instructions lack explicit boundary markers or directives for the agent to ignore instructions embedded within the processed raw material or article files.\n
- Capability inventory: The skill possesses the capability to read from and write to the local file system based on user-provided paths.\n
- Sanitization: No sanitization or filtering logic is specified for the content retrieved from the files before it influences the model's output generation.
Audit Metadata