Skills
skills/saaspegasus/django-skills/upgrade-js-deps/Gen Agent Trust Hub

upgrade-js-deps

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • EXTERNAL_DOWNLOADS (HIGH): The skill utilizes npx npm-check-updates and make npm-install, which download and execute code from the npm registry. This exposes the environment to supply-chain attacks or dependency confusion.
  • REMOTE_CODE_EXECUTION (HIGH): By running make test and make npm-build after modifying dependencies, the skill may execute arbitrary code introduced during the upgrade process via install scripts or test code.
  • COMMAND_EXECUTION (MEDIUM): The skill grants the agent authority to execute make and npx with wildcard parameters, providing a broad surface for command execution.
  • INDIRECT PROMPT INJECTION (HIGH): (Category 8) The skill processes untrusted output from external tools and package metadata. Ingestion points: SKILL.md logic processes tool output from npx and make. Boundary markers: None present. Capability inventory: Arbitrary subprocess execution via make and npx tools. Sanitization: None detected. Malicious data in package versions or tool logs could subvert agent logic to perform unauthorized actions.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 16, 2026, 10:12 AM