write-article
Pass
Audited by Gen Agent Trust Hub on Jul 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues, obfuscation, or malicious intent were identified. The skill performs benign article restructuring and editing tasks as described.
- [PROMPT_INJECTION]: The skill processes external text provided by users, which represents an indirect prompt injection surface. However, its operations are strictly focused on editorial improvements and structural modeling.
- Ingestion points: Content is ingested from files via the 'Read' tool or direct text input (SKILL.md).
- Boundary markers: The skill does not implement specific delimiters to isolate external content from its instructions.
- Capability inventory: The skill uses 'Read', 'Edit', 'Write', and 'AskUserQuestion' tools to process and modify text.
- Sanitization: No explicit sanitization or filtering of the ingested content is defined.
Audit Metadata