indykite-ciq-create-relationship

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides a bash helper script (scripts/execute.sh) and documentation examples that utilize curl and jq to interact with IndyKite service endpoints. This execution is limited to the skill's primary function of managing cloud-based graph resources.
  • [EXTERNAL_DOWNLOADS]: The skill documentation and scripts facilitate network requests to the official IndyKite regional API servers (eu.api.indykite.com and us.api.indykite.com). These communications are necessary for the skill's functionality and target verified vendor infrastructure.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided data through input_params to populate API requests, which represents an attack surface for indirect instructions.
  • Ingestion points: External data enters the agent context via JSON files or standard input processed by the scripts/execute.sh script.
  • Boundary markers: The skill does not employ explicit delimiters in the prompt to separate user data from instructions.
  • Capability inventory: The skill is capable of performing network operations via curl and file reads via cat.
  • Sanitization: Documentation instructions recommend the use of jq to safely assemble JSON payloads, which helps prevent malformed data from influencing the request structure.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 09:20 AM
Security Audit — agent-trust-hub — indykite-ciq-create-relationship