method-section-explainer
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill does not exhibit any malicious behaviors such as credential exfiltration, remote code execution, or obfuscation. Its primary functions involve local file manipulation and text processing for scientific writing.
- [PROMPT_INJECTION]: The skill processes untrusted local content (LaTeX files, design docs, and project notes), which creates an attack surface for indirect prompt injection.
- Ingestion points: The skill reads
paper/.agent/writing-contract.md, algorithm specs, design docs, and LaTeX source files. - Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed files.
- Capability inventory: The skill has access to
Write,Edit, andBashtools, which could be leveraged if an indirect injection were successful. - Sanitization: No explicit sanitization or validation of the input file content is performed.
Audit Metadata