paper-analyzer
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Downloads research papers (PDF, HTML, and source files) from arXiv.org, which is an established and well-known academic repository.
- [COMMAND_EXECUTION]: Executes local Python scripts included with the skill to automate the creation of Markdown notes and the update of a knowledge graph.
- [PROMPT_INJECTION]: Presents a surface for indirect prompt injection (Category 8) as it processes data from external research papers. Titles, authors, and other metadata are extracted from untrusted sources and used to generate files and as arguments for internal scripts.
- Ingestion points: arXiv paper content and metadata retrieved via SKILL.md.
- Boundary markers: Absent. The instructions do not define delimiters or provide specific warnings to the agent to disregard instructions found within the processed papers.
- Capability inventory: The skill utilizes Bash for script execution and Write for local file system management.
- Sanitization: Filenames are sanitized for operating system compatibility, but paper metadata is directly interpolated into Markdown templates and shell command strings without additional escaping.
Audit Metadata