thesis-chapter-reconstructor
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface as it is designed to ingest and process untrusted external data.
- Ingestion points: The skill reads user-provided Markdown drafts for thesis chapters and configuration files located in
codex_md/. - Boundary markers: There are no explicit markers or instructions defined in the skill to help the agent distinguish between its operational logic and potentially malicious instructions embedded within the user's thesis drafts.
- Capability inventory: The skill is limited to reading files, rewriting text, and generating output Markdown files. It does not request or use capabilities such as shell execution, network access, or sensitive file system operations.
- Sanitization: The skill does not implement sanitization or validation logic for the input text contents.
Audit Metadata