cn-thesis-literature-review
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not contain any detected malicious patterns such as prompt injection, data exfiltration, or obfuscation. It follows best practices by instructing the agent to use placeholders like '[TBD: ...]' for missing information rather than hallucinating data.
- [DATA_EXPOSURE]: The skill defines local output paths (e.g.,
output/thesis-context/research-lineage.md) for storing research context. This is a standard and safe method for an AI agent to maintain project state within a workspace and does not involve unauthorized data access or external transmission. - [PROMPT_INJECTION]: While the skill is designed to process untrusted external data (such as user-provided thesis drafts or research papers), the instructions provide a strict framework for transformation into structured tables and claim-evidence matrices. This methodology significantly reduces the risk of the agent obeying hidden instructions within the processed data.
Audit Metadata