research-paper-writing
Pass
Audited by Gen Agent Trust Hub on Jul 28, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a potential surface for indirect prompt injection (Category 8). It is designed to ingest and process untrusted external data such as research notes, code results, and slide bullets to generate manuscript sections.
- Ingestion points: User-provided notes, code results, slide bullets, and external website content accessed via the WebFetch tool.
- Boundary markers: The instructions do not define explicit delimiters or instructions for the agent to ignore potentially malicious embedded content within the ingested research data.
- Capability inventory: The skill utilizes Bash, Read, Write, Edit, Glob, Grep, and WebFetch tools, which allow for file system modification and network access.
- Sanitization: No evidence of sanitization, filtering, or validation of the ingested external content is present in the instruction set.
Audit Metadata