kafka-topic-audit

Pass

Audited by Gen Agent Trust Hub on May 15, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes metadata from external Kafka topics. This is an inherent property of auditing tools that read user-provided descriptions and tags.
  • Ingestion points: Metadata including topic descriptions, tags, and schemas are ingested via the mcp__Lenses__list_topic_metadata tool.
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the ingested metadata.
  • Capability inventory: The skill configuration allows for shell access (Bash) and file system interactions (Read, Grep, Glob) alongside the specialized Lenses auditing tools.
  • Sanitization: Ingested metadata is evaluated for completeness and naming conventions without explicit character escaping or sanitization filters.
Audit Metadata
Risk Level
SAFE
Analyzed
May 15, 2026, 12:43 PM