agent-posthog

Pass

Audited by Gen Agent Trust Hub on Aug 31, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources from PostHog, including event names, properties, and person records. This data enters the agent's context through tools like agent-posthog query hogql and agent-posthog persons list. While this is necessary for the skill's function, it represents a surface where untrusted data could potentially contain instructions aimed at the agent.
  • Ingestion points: Data returned from PostHog APIs via the agent-posthog CLI.
  • Boundary markers: No specific delimiters or instructions to ignore embedded content are defined in the skill instructions.
  • Capability inventory: The agent can execute commands through the agent-posthog and mockposthog binaries.
  • Sanitization: The instructions do not specify any validation or sanitization of the data retrieved from the API before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill relies on the execution of the agent-posthog CLI tool to perform all operations, including authentication, schema discovery, and data querying.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 31, 2026, 09:40 PM
Security Audit — agent-trust-hub — agent-posthog