fec-legacy-to-modern-migration
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze and process legacy source code (JavaScript, HTML, CSS, templates), which represents a surface for indirect prompt injection where instructions hidden in code comments or data could influence the agent's migration plan.\n
- Ingestion points: Legacy frontend codebases including JavaScript, jQuery, and server-rendered templates (SKILL.md).\n
- Boundary markers: Absent. There are no instructions for the agent to ignore or delimit embedded natural language instructions within the source code being analyzed.\n
- Capability inventory: File writing (report generation in
reports/directory) and command execution (running Playwright tests).\n - Sanitization: Absent. The skill does not specify methods for sanitizing or validating the input code for malicious prompts before processing.\n- [COMMAND_EXECUTION]: The skill instructs the agent to execute automated browser testing tools to verify functional and visual equivalence during the migration process.\n
- Evidence: Explicitly requires the use of Playwright or equivalent real browser verification methods for critical user processes and visually sensitive pages (SKILL.md).
Audit Metadata