draft
Pass
Audited by Gen Agent Trust Hub on Mar 12, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill is designed to process untrusted user input such as topics, outlines, and draft text to generate academic prose. This creates a surface for indirect prompt injection. 1. Ingestion points: User-provided research questions and outlines mentioned in SKILL.md. 2. Boundary markers: The instructions lack explicit delimiters to separate user data from system commands. 3. Capability inventory: The agent is directed to save drafts to the local workspace as Markdown or export to .docx. 4. Sanitization: No sanitization of user-provided content is defined. This surface is inherent to the skill's primary function and is mitigated by typical model guardrails.
- [NO_CODE]: The skill consists of Markdown-based instructions only and does not include any executable scripts, binaries, or automated tasks.
Audit Metadata