jq-json-lookup

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions define patterns for querying external JSON files, which serves as an ingestion point for untrusted data into the agent's context. \n
  • Ingestion points: The <file> parameter in jq commands within SKILL.md facilitates reading arbitrary JSON content. \n
  • Boundary markers: There are no explicit instructions or delimiters to treat the JSON content as untrusted or to ignore embedded instructions. \n
  • Capability inventory: The skill utilizes the jq command-line utility for data extraction. \n
  • Sanitization: No sanitization or validation of the input JSON structure or content is performed before the agent processes the output.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 01:40 PM
Security Audit — agent-trust-hub — jq-json-lookup