posthog-survey-creator

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes data from external PostHog sources which act as untrusted input surfaces.
  • Ingestion points: Event definitions, property lists, and survey metadata are ingested from PostHog via MCP tools (e.g., posthog:event-definitions-list, posthog:surveys-get-all) as specified in SKILL.md.
  • Boundary markers: The skill instructions in SKILL.md require the agent to present findings for user validation and wait for responses before proceeding.
  • Capability inventory: The SKILL.md file defines the use of posthog:survey-create to write data back to the platform.
  • Sanitization: No explicit sanitization or filtering of tool outputs is implemented in the skill's instructions or scripts.
  • [SAFE]: The skill uses vendor-specific MCP tools (posthog:*) to interact with the PostHog API, which is consistent with its stated purpose and the identity of the author (PostHog). No suspicious network activity to third-party domains or hardcoded credentials were identified.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 12:47 AM
Security Audit — agent-trust-hub — posthog-survey-creator