te-analysis
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill facilitates the use of the te-cli command-line utility to manage reports and dashboards, and to execute data analysis queries.
- [DATA_EXFILTRATION]: The skill allows the agent to execute arbitrary SQL and query report results, which exposes sensitive information within the user's database scope as part of its analytical functionality.
- [PROMPT_INJECTION]: The skill's ingestion of database query results creates a surface for indirect prompt injection. 1. Ingestion points: Data returned from te-cli analysis +query-sql and +query-report-data as seen in references/query-sql.md and references/query-report-data.md. 2. Boundary markers: Absent; the skill does not use delimiters or provide instructions for the agent to distinguish between its own logic and data retrieved from external queries. 3. Capability inventory: Command execution via te-cli, including write operations such as +save-report, +create-dashboard, and +update-dashboard. 4. Sanitization: Absent; there is no mention of validating, filtering, or escaping the data returned from database queries before it is processed by the agent.
Audit Metadata