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
curlto interact with target GraphQL endpoints and test race conditions.\n - Evidence: Examples using
python3to execute theclairvoyance.pysecurity 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 viagrep, and script execution viapython3(SKILL.md).\n - Sanitization: Absent. The skill does not define procedures for validating or sanitizing content retrieved from external targets before processing.
Audit Metadata