filtering-bot-traffic
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing untrusted external data (User Agents and IP addresses) to classify traffic and manage bot filtering rules.
- Ingestion points: Untrusted data enters the agent context via event properties such as $raw_user_agent, $user_agent, and $ip during query execution and rule creation in SKILL.md.
- Boundary markers: The skill does not provide specific instructions to the agent for using delimiters or warnings when handling or displaying these untrusted strings.
- Capability inventory: The agent is granted access to MCP tools (web-analytics-bot-rules-create, web-analytics-bot-rules-destroy) that can modify project-level settings and persist filtering rules.
- Sanitization: While the backend performs validation on rule patterns, the skill lacks specific guidance for the agent to sanitize or escape user-provided inputs before they are incorporated into rules or queries.
Audit Metadata