edit-article
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill contains only natural language instructions for article editing and restructuring. No scripts, binaries, or system-level commands are present.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and rewrite user-provided articles, which constitutes a surface for indirect prompt injection.
- Ingestion points: The article text provided by the user is the primary input source for the editing instructions.
- Boundary markers: None; the instructions do not specify the use of delimiters to isolate the untrusted input text from the agent's instructions.
- Capability inventory: The skill has no tool access, network capabilities, or file system write permissions. It only performs text transformation.
- Sanitization: No input sanitization or validation is defined in the instructions.
Audit Metadata