resume-canvas
Warn
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill executes a PowerShell script using the -ExecutionPolicy Bypass flag, which disables security restrictions intended to prevent the execution of untrusted local scripts.\n- [EXTERNAL_DOWNLOADS]: The skill uses npx to fetch and execute the @chasen-liao/resume-skills package from the npm registry at runtime. These resources are owned by the skill author.\n- [COMMAND_EXECUTION]: The skill executes several command-line operations, including Node.js package execution (npx) and PowerShell script invocation for resume validation, editing, and rendering.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes visual HTML files which represent an attack surface for instructions embedded in data.\n
- Ingestion points: The skill reads and validates visual HTML files provided in the local environment (SKILL.md).\n
- Boundary markers: Uses a structured editing protocol with specific data-resume-editor-id attributes on leaf elements to define editable fields (SKILL.md).\n
- Capability inventory: The skill can execute shell commands via npx and PowerShell and perform file system writes back to the HTML resume (SKILL.md).\n
- Sanitization: Includes a Fact re-validation loop to check for unverified content changes before finalizing the resume (SKILL.md).
Audit Metadata