figure-table-quality
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted content from the user's project files which could theoretically contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill reads
.texsource files and figure generation scripts (e.g., Matplotlib, R, or Gnuplot scripts) to extract layout parameters. - Boundary markers: There are no specific delimiters or instructions provided to the agent to disregard natural language commands that might be embedded within comments in the source scripts or TeX files.
- Capability inventory: The skill has the authority to modify files via "Auto-Fix Rules," including adjusting font rotations, figure sizes, and label text.
- Sanitization: There is no evidence of sanitization or filtering of the content extracted from the figure scripts before it is used to determine audit results or applied fixes.
Audit Metadata