kafka-consumer-lag
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources (Kafka topics) which presents an attack surface for indirect prompt injection.
- Ingestion points: The
mcp__Lenses__execute_sqltool is used in Step 4 to sample recent messages from Kafka topics (SELECT * FROM {topic} LIMIT 5). - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential instructions embedded within the sampled Kafka messages.
- Capability inventory: The skill has access to file system tools (
Read,Grep,Glob,Bash) and various Kafka management tools through the Lenses MCP server. - Sanitization: No specific sanitization or validation of the message content is mentioned before the agent processes it for reporting.
- Risk Assessment: While the skill ingests external data, its purpose is purely diagnostic and reporting-oriented, with no instructions to execute actions based on message content. This represents a standard risk surface for data-processing skills.
Audit Metadata