paper-2-web
Fail
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill directs the agent to clone an external, unverified repository from https://github.com/YuhangChen1/Paper2All.git during the setup process.
- [REMOTE_CODE_EXECUTION]: The workflow involves installing dependencies and executing scripts, including pipeline_all.py and pipeline_light.py, from the unvetted external repository.
- [PROMPT_INJECTION]: The skill exhibits an Indirect Prompt Injection surface.
- Ingestion points: Processes LaTeX and PDF paper source files provided by the user.
- Boundary markers: Absent; no delimiters or instructions are provided to prevent the agent from following instructions embedded within the paper content.
- Capability inventory: Uses the Bash tool to execute processing scripts and manage local files.
- Sanitization: No explicit sanitization or validation of paper content is mentioned before it is processed by the pipeline.
Recommendations
- AI detected serious security threats
Audit Metadata