kafka-docs

Pass

Audited by Gen Agent Trust Hub on Sep 7, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to fetch and process content from external sources (Apache Kafka documentation) which constitutes an indirect prompt injection surface.
  • Ingestion points: The agent reads web pages from kafka.apache.org based on user queries to ground its answers.
  • Capability inventory: The skill workflow involves searching and opening documentation pages across SKILL.md and references/topic-map.md to provide answers.
  • Boundary markers: The instructions lack specific structural delimiters (like XML tags or clear separators) to isolate retrieved documentation content from the agent's internal reasoning.
  • Sanitization: No explicit sanitization or filtering of the retrieved documentation content is specified in the skill's instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 7, 2026, 11:52 AM
Security Audit — agent-trust-hub — kafka-docs