tw-research-submission-checklist
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides a structured framework for academic manuscript review, covering formatting, citation consistency, and ethical compliance. It references local documentation to guide the analysis and does not perform network operations or access sensitive system paths.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied academic papers and abstracts to perform its analysis, which constitutes an ingestion point for potentially untrusted data.\n
- Ingestion points: Manuscript PDF or text content provided by the user in SKILL.md Step 1.\n
- Boundary markers: Absent; the instructions do not define explicit delimiters to isolate user-provided text from the agent's logic, relying on the model's instruction-following capabilities.\n
- Capability inventory: The skill is granted access to Bash, Read, and Write tools in the allowed-tools configuration.\n
- Sanitization: There is no evidence of input validation or content filtering for the manuscript text.
Audit Metadata