paper-polish-workflow

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external, untrusted data from user-provided paper drafts and PDF reference documents, creating a potential surface for instructions embedded within the text to influence agent behavior.
  • Ingestion points: User-provided text, file paths, and PDF reference papers described in Step 1 of the workflow.
  • Boundary markers: The instructions do not specify the use of delimiters or specific instructions to the agent to disregard commands within the processed text.
  • Capability inventory: The skill utilizes the Read tool to ingest data and describes writing content to new files (*_polished.md).
  • Sanitization: There are no explicit validation or sanitization steps mentioned for the content being processed.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 02:30 PM
Security Audit — agent-trust-hub — paper-polish-workflow