json-transform

Pass

Audited by Gen Agent Trust Hub on Jun 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill documents standard usage of the jq utility for processing JSON files located within a restricted shared volume ({{SHARED_VOLUME}}). All operations are confined to this designated environment.
  • [COMMAND_EXECUTION]: Shell-based execution of jq is used to transform and query data, which is necessary for the skill's intended functionality.
  • [PROMPT_INJECTION]: The skill interacts with untrusted data in the shared volume, which represents a potential surface for indirect prompt injection.
  • Ingestion points: Untrusted JSON files located in {{SHARED_VOLUME}}/input/.
  • Boundary markers: None provided in the instructions to isolate the agent from instructions potentially embedded within the JSON data.
  • Capability inventory: Execution of the jq utility via the shell.
  • Sanitization: No validation or sanitization of the JSON content is performed before it is processed or displayed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 16, 2026, 09:08 AM
Security Audit — agent-trust-hub — json-transform