paper-writing-assistant
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: Indirect Prompt Injection Surface. The skill is designed to ingest and process external data sources which could potentially contain malicious instructions.
- Ingestion points: Paper source files (main.tex, paper.tex, sections/*.tex) and experimental result artifacts (CSVs).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within ingested file content.
- Capability inventory: The agent has access to Read, Write, Edit, Bash, Glob, WebSearch, and WebFetch tools.
- Sanitization: There is no specified logic for sanitizing or validating the content of user-provided paper files.
- [SAFE]: Trusted External References. The skill correctly identifies and utilizes well-known, authoritative academic sources for writing exemplars and guidelines. These include the ACL Anthology, OpenReview, NeurIPS, and CVF Open Access. References to these services are documented neutrally and are consistent with the skill's stated purpose.
Audit Metadata