perses-dashboard-review
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes external dashboard definitions.
- Ingestion points: Dashboard JSON is retrieved in Phase 1 (FETCH) using MCP tools or the
perclicommand-line utility. - Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the dashboard metadata (e.g., in panel descriptions or titles).
- Capability inventory: The skill is granted access to powerful tools including
Bash,Write,Edit, andAgent(sub-agent invocation). - Sanitization: There is no mention of sanitizing or escaping dashboard content before it is passed to the LLM for analysis.
- [COMMAND_EXECUTION]: The skill is configured to use the
Bashtool to interact with thepercliCLI for fetching and applying dashboard configurations. This is an intended behavior for its primary purpose as a dashboard engineer tool.
Audit Metadata