filtering-bot-traffic
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the AI agent to process and analyze User-Agent strings, which are externally controlled by web visitors and bots. While this is the intended purpose of the skill, it creates a surface where malicious instructions could theoretically be embedded in the data stream.
- Ingestion points: The agent reads from
properties.$raw_user_agentandproperties.$user_agentwithin the PostHog event data. - Boundary markers: None are explicitly defined in the provided instructions for these fields.
- Capability inventory: The skill uses analytical capabilities including
TrendsQuery,FunnelsQuery, and HogQL functions such asisLikelyBot(),getBotName(), andgetTrafficType()to process the data. - Sanitization: The skill does not explicitly describe sanitization steps for the user-agent content, relying on the platform's query engine safety.
Audit Metadata