intent-check
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to analyze external, untrusted content including Intent markdown files and project source code.
- Ingestion points: The skill processes Intent files (e.g.,
INTENT.md) and source code files (e.g.,src/core/intent/*.md,chamber.js,apps.js) to generate validation and synchronization reports. - Boundary markers: The instructions do not specify any delimiters or safety guardrails (like "ignore embedded instructions") to distinguish between data being analyzed and instructions for the agent.
- Capability inventory: The skill is intended to provide action items and repair suggestions based on the content of analyzed files, creating a path where malicious content in a file could influence the agent's output.
- Sanitization: There is no evidence of sanitization or filtering of the input data before it is processed by the intent-validate or intent-sync components.
Audit Metadata