NYC

article-extractor

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • COMMAND_EXECUTION (MEDIUM): The skill interpolates the ARTICLE_URL variable directly into bash command strings (e.g., reader "$ARTICLE_URL"). This creates a shell injection vulnerability if a URL contains command separators like semicolons or pipes.\n- EXTERNAL_DOWNLOADS (MEDIUM): The instructions suggest installing global packages from NPM and PyPI (npm install -g, pip3 install) at runtime. These dependencies are not version-pinned and originate from public registries, posing a supply chain risk.\n- PROMPT_INJECTION (LOW): Risk of Indirect Prompt Injection (Category 8) from processed web content. The agent reads and displays a preview of untrusted data from external URLs.\n
  • Ingestion points: Web content fetched from the user-provided URL in the Complete Workflow section.\n
  • Boundary markers: No delimiters or warnings are used when presenting extracted content to the agent.\n
  • Capability inventory: The agent has access to powerful tools like Bash and Write.\n
  • Sanitization: No sanitization of the article content is performed; only the output filename is cleaned.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 05:11 PM