academic-research-writer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE] (SAFE): No malicious behavior, prompt injections, or unauthorized data access patterns were identified in the instructions or scripts. The skill operates as intended for academic research support and follows legitimate pedagogical guidelines.
- [Indirect Prompt Injection] (SAFE): The skill possesses a standard vulnerability surface as it ingests untrusted data from external academic databases via web search tools. This is an inherent risk of research agents. 1. Ingestion points: Workflow step 3 in SKILL.md and implementation approach. 2. Boundary markers: Absent; search results are processed directly by the agent. 3. Capability inventory: Use of web_search and web_fetch tools, and execution of the local ieee_formatter.py script. 4. Sanitization: Absent; relying on the model's internal safety guardrails for ingested content.
Audit Metadata