migrate-to-skills

Pass

Audited by Gen Agent Trust Hub on Mar 18, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the delete tool to remove original configuration files after migration is complete. While this is the intended functionality, it constitutes a destructive filesystem operation.- [PROMPT_INJECTION]: The skill includes strong instructional language ('CRITICAL', 'IMPORTANT') to define strict processing rules, which is standard for formatting tasks but involves override-style markers.- [PROMPT_INJECTION]: The skill processes untrusted data from local rule and command files, creating a surface for indirect prompt injection.
  • Ingestion points: The agent reads content from .mdc and .md files located in {workspaceFolder} and ~/.cursor/ directories.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands embedded within the files being migrated.
  • Capability inventory: The agent has access to read, edit, and delete tools, which could be misused if instructions within the migrated files influence agent behavior.
  • Sanitization: No sanitization or validation of the input file content is performed; the skill mandates character-for-character verbatim copying.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 18, 2026, 02:41 AM
Security Audit — agent-trust-hub — migrate-to-skills