garchi-cms-content
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill directs the agent to ingest untrusted data by reading source code from
node_modules,vendor, and the local codebase to provide integration assistance. - Ingestion points: Local codebase files and dependency directories (
node_modules,vendor). - Boundary markers: Absent. The instructions do not include delimiters or warnings to ignore instructions embedded within the code or comments it reads.
- Capability inventory: File reading and code generation capabilities are used to process the ingested content.
- Sanitization: Absent. The agent is instructed to use the discovered code directly as a reference for generating output.
Audit Metadata