The Agent Skills Directory

[SAFE]: No malicious patterns or security threats were found. The skill operates within the expected scope of a developer tool for the AG Grid product suite, using official documentation and providing best practice recommendations.
[INDIRECT_PROMPT_INJECTION]: The skill reads project configuration data from package.json to identify library versions and frameworks. This is a standard functional requirement for the skill's purpose, though it technically establishes a surface for untrusted data ingestion. Ingestion points: package.json files (SKILL.md). Boundary markers: Absent. Capability inventory: Writing and editing code, planning features. Sanitization: Absent.

ag-dev