writing-gate-checker
Pass
Audited by Gen Agent Trust Hub on May 1, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes various external project files. \n
- Ingestion points: Reads files from 00-Brief.md, 01-Context/context-packet.md, 02-Drafts/草稿_v*.md, and other project artifacts. \n
- Boundary markers: Absent; the skill does not include specific delimiters or instructions to ignore potential commands embedded in the project files. \n
- Capability inventory: File reading (multiple paths) and file writing (to 03-Reviews/Gate-Check-Report.md). No network or shell execution capabilities are utilized. \n
- Sanitization: Absent; the skill lacks mechanisms to sanitize or validate the content of the files it reads before processing. \n- [COMMAND_EXECUTION]: The skill performs file system operations (reading and writing) based on the project structure. While these are legitimate for its role as an auditor, they represent the capability to modify the local file system.
Audit Metadata