competitor-skill

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads abstract drawings from Patsnap's content delivery network (zhihuiya.com) during report generation. This is a standard functional requirement for including patent visuals in reports.
  • [DATA_EXPOSURE_&_EXFILTRATION]: Instructions in SKILL.md guide users to store their own API keys in a local .env file within the scripts/ directory. This follows best practices for secret management by keeping credentials out of code and in the local environment only.
  • [COMMAND_EXECUTION]: The skill uses shell scripts (run.sh) to orchestrate Python execution and environment setup. The usage of uv run or pip install is restricted to legitimate dependencies (requests, python-dotenv).
  • [INDIRECT_PROMPT_INJECTION]: The skill processes patent abstracts and bibliographic data which are sourced from the Patsnap database. While this data is external, it is limited to structured patent information and used to generate Markdown/HTML reports, presenting a minimal attack surface.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 01:22 AM