anfra-convert-looker

Warn

Audited by Gen Agent Trust Hub on Nov 19, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/lib/sources.mjs utilizes child_process.execFileSync to execute git commands (such as rev-parse, diff, and ls-files) to retrieve repository metadata and commit hashes. While this is used for an audit trail, spawning subprocesses with system tools is a sensitive operation.
  • [DYNAMIC_EXECUTION]:
  • The script scripts/lookml-parser/transformations/assemble-models.js dynamically generates regular expressions using new RegExp() based on LookML include patterns found in user files.
  • The utility scripts/lookml-parser/maybe-yaml-parse/index.js performs dynamic loading of the yaml library using the import() statement.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow where a second pass is performed by an AI agent (subagent) that reads generated AML files. These files contain reprinted LookML snippets from user-provided files within TODO and REVIEW comments. A maliciously crafted LookML file could attempt to inject instructions to manipulate the subagent's logic during this phase.
  • Ingestion points: LookML files (.lkml) are read from the filesystem by scripts/convert.mjs.
  • Boundary markers: User-provided SQL and LookML snippets are wrapped inside // TODO(lookml-to-aml:...) or // REVIEW(lookml-to-aml:...) blocks.
  • Capability inventory: The skill has read/write access to the local filesystem and the ability to execute shell commands via execFileSync.
  • Sanitization: LookML content is reprinted from a parsed AST, providing basic structural normalization, but no semantic sanitization is applied to the content placed in comments.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Nov 19, 2026, 08:49 PM