credo-paper-plan
Pass
Audited by Gen Agent Trust Hub on Oct 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as an instructional guide for academic writing tasks, such as planning arguments, storyboarding figures, and responding to peer reviews. It does not contain any code or executable logic.
- [EXTERNAL_DOWNLOADS]: The file 'references/peer-review-response.md' contains URLs to GitHub repositories (github.com/msimchowitz/writing-skills and github.com/wanshuiyin/Auto-claude-code-research-in-sleep). These are provided strictly as source citations for the methodology and are not downloaded or executed by the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-provided research paper drafts (ingestion point: SKILL.md). While the skill lacks explicit boundary markers or sanitization for this input, it also possesses no high-risk capabilities—such as file writing, network access, or command execution—that could be exploited by malicious content within a draft. The risk is assessed as safe given the lack of side-effect tools.
Audit Metadata