update-dependencies

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • EXTERNAL_DOWNLOADS (LOW): The skill instructs the agent to install and execute third-party utilities such as npm-check-updates, cargo-audit, and pip-audit. These are standard tools for dependency management but involve the execution of code from remote package registries. Additionally, scripts/analyze.ts is referenced in the documentation but was not provided in the analyzed bundle.
  • COMMAND_EXECUTION (SAFE): The skill executes shell commands for package managers (npm, bun, pnpm, uv, poetry, cargo) and Git/GitHub CLI operations. These commands are consistent with the skill's primary purpose and do not show signs of malicious intent.
  • PROMPT_INJECTION (LOW): The skill is susceptible to Indirect Prompt Injection (Category 8) because it fetches and processes external release notes and changelogs to perform risk assessments.
  • Ingestion points: Fetches external metadata and changelog content via gh api and npm view from remote repositories.
  • Boundary markers: Absent. The instructions do not provide delimiters or specific ignore-rules for the agent when processing external text.
  • Capability inventory: High-impact capabilities including arbitrary shell execution for package updates, test execution, and automated PR creation.
  • Sanitization: None detected. External changelog text is ingested and summarized directly by the agent without prior filtering or sanitization.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:33 PM