de-ai-writer
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied Chinese drafts for diagnostic scoring and rewriting. This represents an indirect prompt injection surface where instructions hidden within the user-provided content could theoretically attempt to influence the agent's behavior. However, the risk is negligible as the skill lacks dangerous capabilities such as file system access, network operations, or shell execution.
- Ingestion points: User-provided Chinese drafts processed during the scoring (Step 1) and rewriting (Step 2) phases described in
SKILL.md. - Boundary markers: No explicit delimiters or boundary instructions are defined to separate user content from system instructions.
- Capability inventory: The skill is limited to text analysis and generation; it does not perform network requests, file writes, or subprocess execution.
- Sanitization: No sanitization or filtering of input text is implemented.
Audit Metadata