paper-polish-workflow
Pass
Audited by Gen Agent Trust Hub on Mar 23, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes external text and PDF files provided by the user, which presents a surface for indirect prompt injection where malicious instructions could be embedded within the academic content to manipulate the agent's behavior. \n- Ingestion points: Step 1 (Collect Context) involves reading input content from specified file paths or pasted text using the Read tool. \n- Boundary markers: The instructions lack explicit delimiters or mandatory warnings to ignore instructions found within the user-provided content. \n- Capability inventory: The skill has the capability to read files from the filesystem and write the final output to a new file (*_polished.md). \n- Sanitization: No sanitization or validation of the input content is performed before processing.
Audit Metadata