create-honeycomb-board
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFE
Full Analysis
- [PROMPT_INJECTION]: The skill analyzes local source code and documentation to generate dashboard descriptions and text panels. This creates a potential surface for indirect prompt injection if an attacker can place malicious instructions within the project's files.\n
- Ingestion points: Files accessed via
Read,Grep, andGlobtools inSKILL.md.\n - Boundary markers: None explicitly defined for the ingested file content.\n
- Capability inventory:
mcp__honeycomb__create_boardandmcp__honeycomb__run_querytools are used to interact with the Honeycomb API.\n - Sanitization: The skill relies on a mandatory 'Show the proposed board to the user' step as its primary safety mechanism, which requires explicit user approval of the generated content before board creation.
Audit Metadata