update-integrations-prs

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • External Data Retrieval: The skill fetches package download statistics from pypistats.org and npmjs.org using curl. These are well-known, established services used to retrieve package metadata for policy verification.
  • Local Command Execution: The skill uses python3 to parse JSON data retrieved from package registries. The Python execution uses a static, hardcoded script to calculate download totals, which is a common pattern for processing API responses in development workflows.
  • Indirect Prompt Injection Surface: As the skill is designed to process contributor pull requests, it ingests external data such as PR titles, bodies, and file changes via gh and git. While this is the primary purpose of the skill, standard review practices are recommended when an agent processes untrusted external content.
  • GitHub Operations: The skill performs repository management tasks including rebasing branches and viewing PR metadata. It includes safety checks, such as instructing the agent not to push changes unless explicitly requested by the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 05:49 PM