content-refinement-agent
Step 5 of the PaperOrchestra pipeline (arXiv:2604.05018). Iteratively refine drafts/paper.tex by simulating peer review and applying targeted revisions, with strict accept/revert halt rules. Maintains a worklog and snapshots each iteration so revert is real, not symbolic. TRIGGER when the orchest...
Install this skill
or
99/100
Security score
The content-refinement-agent skill was audited on Aug 4, 2026 and we found 1 security issue across 1 threat category. Review the findings below before installing.
Categories Tested
Security Issues
low line 203
Command substitution pattern
SourceSKILL.md
| 201 | EXIT=$? |
| 202 | # Update streak for next iteration: |
| 203 | CONSECUTIVE_SMALL=$(python3 -c " |
| 204 | import json |
| 205 | d = json.load(open('workspace/refinement/iter<N>/delta.json')) |
Scanned on Aug 4, 2026
View Security Dashboard