writing-shape
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill reads raw markdown files provided by the user to extract content for article generation. This ingestion creates a surface for indirect prompt injection where malicious instructions embedded in the input material could override the skill's logic.
- Ingestion points: Raw material markdown files read by the agent (SKILL.md).
- Boundary markers: No explicit boundary markers or instructions to ignore embedded commands are present in the processing logic.
- Capability inventory: The skill requires permissions to read from the local file system and write to a user-specified article file.
- Sanitization: The skill does not perform validation or sanitization of the input text before processing.
Audit Metadata