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.$raw_user_agent and properties.$user_agent within 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 as isLikelyBot(), getBotName(), and getTrafficType() 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
Risk Level
SAFE
Analyzed
Sep 10, 2026, 03:59 PM
Security Audit — agent-trust-hub — filtering-bot-traffic