posthog-enterprise-rbac

Pass

Audited by Gen Agent Trust Hub on Mar 10, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill represents an attack surface for indirect prompt injection.
  • Ingestion points: Configuration data for SSO and role mappings provided by users or external sources are ingested during the setup process.
  • Boundary markers: No delimiters or specific instructions are present to isolate untrusted configuration data from the agent's core instructions.
  • Capability inventory: The skill's authorization to use 'Write' and 'Edit' tools allows the agent to modify configuration files, which could be exploited if malicious input is provided.
  • Sanitization: No sanitization or validation logic is provided in the boilerplate code to handle potentially malicious configuration inputs.
  • [SAFE]: The skill adheres to security best practices by using environment variables for sensitive credentials such as 'SAML_CERT' and 'POSTHOG_OAUTH_CLIENT_SECRET' instead of hardcoding them.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 10, 2026, 06:54 PM