paper-writing-contract-planner
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, including prompt injections, credential harvesting, or unauthorized network operations, were detected. The skill's instructions are consistent with its stated goal of helping authors plan their research papers.
- [PROMPT_INJECTION]: Analyzed the surface for indirect prompt injection. The skill ingests untrusted data from the web using WebFetch and reads existing project files such as paper drafts. Ingestion points: Web content and local .tex files. Boundary markers: Absent. Sanitization: Not specified. Capability inventory: Bash, Write, Edit, WebSearch, WebFetch. While this ingestion surface exists, it is an essential part of the skill's research function and does not show signs of being exploitable for malicious purposes within the context of the provided instructions.
Audit Metadata