kai-data-dashboard
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local Python script
scripts/quality_gates/audit_provenance_lint.pyfound within the Kai environment. This script is used to validate audit data and is part of the skill's intended quality control workflow. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from various sources (CSV, JSON, Markdown) to generate dashboards. This ingestion represents a potential attack surface for indirect prompt injection if these files contain malicious instructions.
- Ingestion points: The skill reads from paths like
workspace/sdr-operator/<package-slug>/and files such askai-data.json,audit-data.json, and various CSV exports. - Boundary markers: There are no explicit delimiters or specific instructions for the agent to ignore natural language instructions found within the ingested data files.
- Capability inventory: The skill can read local files, write new files to a
dashboard/directory, and execute a local Python script. - Sanitization: While there are quality gates to mask sensitive data, there is no technical sanitization described to prevent the processing of malicious instructions embedded in the source data.
Audit Metadata