kafka
Pass
Audited by Gen Agent Trust Hub on Mar 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates standard Kafka management operations using system utilities. All operations are transparently described and limited to local network communication.
- [COMMAND_EXECUTION]: The skill uses curl and jq to interact with a local REST API. No arbitrary or dangerous command execution was detected.
- [DATA_EXFILTRATION]: Network communication is restricted to localhost:8082. There is no evidence of sensitive data being sent to external or untrusted domains.
- [PROMPT_INJECTION]: The skill retrieves data from an external source (Kafka topics), which is a surface for indirect prompt injection, but it does not provide an exploitable path for this data to affect the agent's core instructions or execute unauthorized actions. (1) Ingestion points: Kafka message content consumed via curl in SKILL.md. (2) Boundary markers: Not present. (3) Capability inventory: curl and jq for local communication; no high-risk capabilities like file system writes or arbitrary code execution. (4) Sanitization: None.
Audit Metadata