cn-thesis-formula
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill uses standard instructional language to guide the AI in formula drafting and review. No attempts to override safety filters, bypass constraints, or extract system prompts were detected.
- [DATA_EXFILTRATION]: There are no hardcoded credentials, sensitive file path accesses, or unauthorized network operations. The skill solely processes user-provided mathematical notation.
- [OBFUSCATION]: Analysis of the skill instructions and metadata revealed no base64-encoded commands, zero-width characters, homoglyphs, or other obfuscation techniques.
- [REMOTE_CODE_EXECUTION]: The skill does not perform any remote package installations or script executions. Dependencies listed in the manifest refer to local shared components within the project structure rather than external URLs.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-supplied formulas and thesis prose (ingestion points in chat input). While it does not implement explicit sanitization for this data, it lacks any high-privilege capabilities such as file system writing, network requests, or subprocess execution that could be exploited by embedded instructions. The workflow emphasizes the use of LaTeX delimiters and explicit markers for missing information, which provides structural isolation.
Audit Metadata