paper-analyzer
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches academic paper PDFs and metadata from the official arXiv repository. These downloads are essential for the skill's primary function of paper analysis and originate from a well-known service.
- [COMMAND_EXECUTION]: Executes local Python scripts to automate note generation and graph maintenance within an Obsidian vault. The shell commands use variable quoting to mitigate standard argument injection vulnerabilities.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from academic papers, creating a potential vector where malicious content within a paper could attempt to influence the agent's analysis.
- Ingestion points: Paper content and metadata are downloaded from arXiv and processed by the agent.
- Boundary markers: None explicitly defined in the provided instruction set.
- Capability inventory: The skill possesses the ability to write files to the local file system and perform network requests to arXiv.
- Sanitization: The note generation script sanitizes paper titles before using them in file paths to remove shell-sensitive characters.
Audit Metadata