posthog-onboarding

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were identified in the skill instructions or reference files. The skill correctly uses vendor-specific resources and maintains a professional, task-oriented scope with legitimate business purposes.
  • [INDIRECT_PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its reliance on external research and user-provided inputs, which is standard for research-oriented assistants.
  • Ingestion points: Step 1 (Research) and Step 2 (Current State) in SKILL.md ingest data from external domains and user descriptions.
  • Boundary markers: Absent; the prompt does not utilize specific delimiters to isolate external content from instructions.
  • Capability inventory: The skill is restricted to generating text-based improvement plans (SKILL.md Step 7). It lacks dangerous capabilities such as shell access, arbitrary code execution, or network exfiltration tools.
  • Sanitization: Absent; there is no mention of filtering or validating the ingested content before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 05:26 PM