gron Greppable JSON Flattener

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly states the tool "supports reading from files, URLs, and standard input," meaning the skill can ingest JSON from arbitrary public URLs (open web) which the agent would parse and act upon, exposing it to untrusted third-party content that could carry indirect prompt-injection instructions.