proofread-non-native
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied text for evaluation and revision, which introduces a potential attack surface for indirect prompt injection. \n
- Ingestion points: The skill ingests user-provided text as described in
SKILL.mdfor proofreading and evaluation. \n - Boundary markers: The output template uses markdown delimiters (
---), but there are no specific instructions to the model to ignore or escape instructions contained within the user's input. \n - Capability inventory: The skill has no defined capabilities for system commands, file writes, or external network calls. \n
- Sanitization: No validation or sanitization of the user input is specified. \n- [NO_CODE]: The skill consists entirely of natural language instructions and configuration files. It does not include any scripts (Python, JavaScript, shell) or compiled binaries.
Audit Metadata