cn-thesis-revision
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes untrusted user-provided thesis content and advisor comments without specific boundary markers or delimiters. While the skill includes extensive rules to minimize changes and maintain document integrity, there is an inherent surface for indirect prompt injection where instructions embedded in a thesis or comment could influence the agent's behavior.
- Ingestion points: Thesis drafts, advisor comments, and
.docxfiles are primary inputs to the workflow defined inworkflow.mdandSKILL.md. - Boundary markers: The instructions do not specify the use of delimiters (e.g., XML tags or block markers) to separate the thesis content from the agent's operational instructions when processing inputs.
- Capability inventory: The skill has capabilities to modify the file system (creating revised
.docxfiles) and references the execution of local analysis scripts (scripts/docx_review_stub.py). - Sanitization: No explicit sanitization, escaping, or validation logic for external thesis content is defined in the instructions.
Audit Metadata