hunt-graphql

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides templates and instructions for executing shell commands to perform reconnaissance and vulnerability testing.\n
  • Evidence: Examples using curl to interact with target GraphQL endpoints and test race conditions.\n
  • Evidence: Examples using python3 to execute the clairvoyance.py security tool for schema enumeration.\n- [INDIRECT_PROMPT_INJECTION]: The hunting methodology involves the analysis of untrusted data from external targets, creating a vulnerability surface for indirect injection.\n
  • Ingestion points: The agent is instructed to fetch and analyze GraphQL introspection responses, HTTP headers, and JavaScript source code from external target domains (SKILL.md).\n
  • Boundary markers: Absent. There are no guidelines provided for the agent to distinguish between its instructions and the external data it processes.\n
  • Capability inventory: The skill utilizes network access via curl, file analysis via grep, and script execution via python3 (SKILL.md).\n
  • Sanitization: Absent. The skill does not define procedures for validating or sanitizing content retrieved from external targets before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 05:31 AM
Security Audit — agent-trust-hub — hunt-graphql