thesis-tex-writeback
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection as it processes content from external markdown files and writes them to the LaTeX delivery layer.
- Ingestion points: The skill ingests data from
codex_md/00_thesis_outline.md,codex_md/terminology_glossary.md,codex_md/symbol_metric_table.md,codex_md/figure_plan.md, and various chapter-level markdown files. - Boundary markers: There are no explicit instructions or delimiters defined to help the agent distinguish between the thesis content (data) and the instructions governing the writeback process (commands).
- Capability inventory: The skill is capable of performing file system write operations to the
chapters/*.texdirectory. - Sanitization: The instructions do not mention any sanitization, escaping, or validation of the markdown content before it is interpolated and written to the TeX files.
Audit Metadata