indykite-authzen-list-policies

Pass

Audited by Gen Agent Trust Hub on Sep 24, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes a shell script scripts/list-policies.sh that executes the curl command to interact with the IndyKite REST API. This script implements security best practices, such as host pinning and input validation, to ensure safe execution.
  • [INDIRECT_PROMPT_INJECTION]: The skill possesses a data ingestion surface through the processing of JSON authorization policies.
  • Ingestion points: Data enters the system via the GET /access/v1/policies API response in scripts/list-policies.sh.
  • Boundary markers: The skill instructions utilize jq recipes for structured data extraction, which helps maintain a boundary between data and instructions.
  • Capability inventory: The skill employs curl for network requests and jq for JSON processing.
  • Sanitization: The shell script validates the subject_type argument against a strict regular expression (^[A-Za-z_][A-Za-z0-9_]{1,63}$) before it is used in the network request.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 24, 2026, 07:09 AM
Security Audit — agent-trust-hub — indykite-authzen-list-policies