paper-plan

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: The skill operates as an academic aid, processing research documents into outlines without any detected malicious intent.
  • [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection by reading research files to generate content. 1. Ingestion points: NARRATIVE_REPORT.md, STORY.md, AUTO_REVIEW.md, IDEA_REPORT.md, findings.md (SKILL.md). 2. Boundary markers: Absent. 3. Capability inventory: Bash, Write, WebSearch, WebFetch, mcp__codex__codex (SKILL.md). 4. Sanitization: Absent.
  • [EXTERNAL_DOWNLOADS]: The skill references external GitHub repositories for academic methodology and research protocols. No external code is downloaded or executed.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 03:14 AM