thesis-citation-enhance-review
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied thesis content in Markdown or TeX formats, which are untrusted data sources.
- Ingestion points: SKILL.md lists Markdown and TeX versions of the thesis as inputs.
- Boundary markers: No specific boundary markers or instructions to ignore embedded commands are defined for the input data to separate it from agent instructions.
- Capability inventory: The skill is designed to read and modify thesis documents and BibTeX files across the workspace.
- Sanitization: No sanitization, escaping, or validation of the input text is specified to prevent the execution of potential instructions embedded within the thesis content.
Audit Metadata