inth
Pass
Audited by Gen Agent Trust Hub on Jun 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
curlto perform authenticated API requests andjqfor parsing JSON responses. - [COMMAND_EXECUTION]: It includes a diagnostic command
zero doctorto help users verify their environment and connector status. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it processes output from external API endpoints.
- Ingestion points: Remote API responses fetched via
curlinSKILL.md. - Boundary markers: Absent; no delimiters or instructions are used to distinguish API data from instructions.
- Capability inventory: Network operations (
curl) and CLI tool execution (zero doctor) are present inSKILL.md. - Sanitization: Absent; the skill does not perform validation or sanitization on the external data before it is processed by the agent.
Audit Metadata