enonic-guillotine-query-builder
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute a local Node.js script
scripts/find-guillotine-targets.mjs. This script performs a recursive scan of the local filesystem to inventory files containing specific library markers. - [DYNAMIC_EXECUTION]: The skill generates project-specific TypeScript code by populating placeholders within a provided template file (
assets/guillotine-query.template.ts) based on discovered content types. - [INDIRECT_PROMPT_INJECTION]: The agent is directed to read and analyze various code and configuration files within the workspace to determine API versions and schema definitions.
- Ingestion points: Files with extensions like
.ts,.js,.graphql, and.xmlthat are flagged as containing Guillotine library markers. - Boundary markers: No explicit delimiters or instructions to ignore embedded prompts are provided when reading these files.
- Capability inventory: Access to the local file system and execution of Node.js scripts.
- Sanitization: No sanitization or validation of the ingested file content is performed before processing.
Audit Metadata