academic-research

Pass

Audited by Gen Agent Trust Hub on Nov 1, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill documentation recommends installing a third-party MCP server (arxiv-mcp-server) from an unofficial GitHub repository (blazickjp/arxiv-mcp-server) using uv or npx.
  • [DATA_EXPOSURE]: The SKILL.md file contains a hardcoded reference to a specific local directory path: ~/Desktop/Aldea/01-Repos/perplexity-clone/model/moba_block_sparse.py. This reveals information about the user's local filesystem structure.
  • [COMMAND_EXECUTION]: The skill executes a custom bash script academic_stealth_fetch.sh which invokes the obscura CLI tool to perform web scraping operations.
  • [DYNAMIC_EXECUTION]: The academic_stealth_fetch.sh script dynamically constructs JavaScript strings and passes them to the obscura tool's --eval flag for execution within a headless browser environment.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external academic sources which could contain malicious instructions.
  • Ingestion points: The skill ingests search results from Exa, paper content via read_paper (ArXiv MCP), and scraped metadata from obscura.
  • Boundary markers: No specific delimiting or safety instructions are provided to the agent for handling these external data streams.
  • Capability inventory: The agent has the ability to search web content, download and read files from the ArXiv repository, and execute shell scripts.
  • Sanitization: Although the scraping script uses JSON.stringify for data formatting, no content filtering or instruction-stripping is performed before the data is presented to the agent's context.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 1, 2026, 10:13 AM