academic-writing-style
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user requirements and local reference files to generate academic documents, creating a surface for indirect prompt injection. 1. Ingestion points: The skill reads content from references/chinese-examples.md, references/english-examples.md, and references/writing-guidelines.md, alongside user-supplied assignment details as specified in SKILL.md. 2. Boundary markers: The instructions do not define explicit delimiters or 'ignore' commands for the content being processed to prevent the agent from following instructions embedded in the data. 3. Capability inventory: The skill is authorized to perform file-writing operations to the outputs/ directory. 4. Sanitization: There are no mentions of input validation or sanitization mechanisms for the data before it is incorporated into the generation process.
Audit Metadata