fix-js-globals
Pass
Audited by Gen Agent Trust Hub on Aug 4, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to run 'npx @ui5/linter --details' and various 'grep' commands to search for legacy code patterns. These commands are standard developer tools and are used appropriately for code analysis and search within the project workspace.
- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by instructing the agent to ingest and process arbitrary JavaScript files from a workspace. Evidence: (1) Ingestion points: JavaScript files in the workspace as defined in SKILL.md; (2) Boundary markers: Absent; (3) Capability inventory: Shell command execution (npx, grep) and file system modification; (4) Sanitization: Absent. This risk is inherent to the skill's primary function of code modernization and transformation and does not indicate malicious intent.
Audit Metadata