Skills
Navigate
skills/indykite/skills/indykite-ciq-add-property/Gen Agent Trust Hub

indykite-ciq-add-property

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The shell script scripts/execute.sh executes curl to send requests to the IndyKite REST API.
  • [EXTERNAL_DOWNLOADS]: The skill requires network access to IndyKite's official regional API endpoints (eu.api.indykite.com and us.api.indykite.com) and dependencies on common system utilities like curl and jq.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface for processing external data through configuration parameters and user tokens.
  • Ingestion points: User-supplied data enters via the input_params file or stdin and the BEARER_TOKEN environment variable in scripts/execute.sh.
  • Boundary markers: The skill uses JSON objects to encapsulate and delimit data values.
  • Capability inventory: The skill has the ability to perform network writes via curl.
  • Sanitization: The instructions recommend using jq for constructing API payloads, ensuring that data is properly formatted as JSON.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:20 AM
Security Audit — agent-trust-hub — indykite-ciq-add-property