draft
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, network requests, or attempts to access sensitive system files. Its instructions are focused exclusively on the task of academic drafting and structuring.
- [PROMPT_INJECTION]: The skill includes an indirect prompt injection surface, as its primary function is to ingest and process external content such as user notes, wiki pages, and documents. While no malicious instructions are present, the skill lacks specific security controls for handling untrusted data.
- Ingestion points: User notes, wiki content, and research documents specified in the description and workflow.
- Boundary markers: Absent; no delimiters or ignore-instructions are used to isolate ingested data from the core drafting instructions.
- Capability inventory: Reads provided research documents and generates structured text output.
- Sanitization: Absent; there is no instruction to validate or escape content retrieved from external files.
Audit Metadata