posthog-analytics

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • PROMPT_INJECTION (HIGH): The skill is vulnerable to Indirect Prompt Injection via untrusted external data ingestion. \n
  • Ingestion points: Untrusted data enters the agent context through event-definitions-list, properties-list, and results from query-run (SKILL.md). \n
  • Boundary markers: No delimiters or explicit instructions to ignore embedded commands are present in the instructions. \n
  • Capability inventory: The skill possesses the capability to write to the local filesystem (.claude/product-context.md) and perform state-changing actions like dashboard-create and experiment-create (SKILL.md). \n
  • Sanitization: No sanitization, escaping, or schema validation is applied to the data strings retrieved from PostHog before they are processed by the agent.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 12:36 AM