paper-draft-consistency-editor
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection attack surface by processing untrusted external content with high-privilege tools.
- Ingestion points: The skill reads LaTeX (.tex) and Markdown (.md) source files, as well as project-specific agent configuration files.
- Boundary markers: The instructions lack explicit delimiters or warnings to treat processed paper content as data rather than instructions, which could allow malicious commands embedded in papers to influence agent behavior.
- Capability inventory: The skill is authorized to use Bash, Write, and Edit tools, providing a pathway for command execution or unauthorized file modification if an injection occurs.
- Sanitization: No content validation or sanitization procedures are defined for the input paper data before processing.
Audit Metadata