pure-admin-crud-generator

Pass

Audited by Gen Agent Trust Hub on Mar 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute local shell commands such as 'rg' (ripgrep), 'awk', and 'pnpm typecheck' to inspect project files and verify the integrity of generated code.
  • [PROMPT_INJECTION]: The skill has an indirect prompt injection attack surface.
  • Ingestion points: It reads and parses 'src/api/swagger/Api.ts' and 'src/api/api.ts'.
  • Boundary markers: Absent; there are no instructions to use delimiters or ignore instructions found within the source files.
  • Capability inventory: The skill can write Vue and TypeScript files to the repository and execute shell commands via pnpm.
  • Sanitization: Absent; the agent is directed to parse the source file contents directly without any pre-processing or validation of the data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 8, 2026, 07:45 PM