using-academic-research
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a descriptive index and organizational framework for academic research tasks. It references legitimate academic tools such as Pandoc and tectonic for formatting and document processing. Analysis of the provided file found no evidence of prompt injection, data exfiltration, or malicious commands.
- [INDIRECT_PROMPT_INJECTION]: The skill's intended purpose involves processing external academic documents and literature, which presents a surface for indirect prompt injection from untrusted research data.
- Ingestion points: External research papers, citation data, and literature sources ingested during the
deep-researchandacademic-paper-reviewerphases (SKILL.md). - Boundary markers: The instructions do not explicitly define boundary markers or delimiters for untrusted data in the provided document.
- Capability inventory: The skill description indicates that the adapted WorkBuddy version utilizes file system tools (Read, Write, Edit) and shell execution (Bash) for tasks like formatting and citation management (SKILL.md).
- Sanitization: The skill outlines principles for "Citation authenticity" and "Semantic Scholar API verification," but does not detail technical sanitization or escaping of ingested text content.
Audit Metadata