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.orgbased on user queries to ground its answers. - Capability inventory: The skill workflow involves searching and opening documentation pages across
SKILL.mdandreferences/topic-map.mdto 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