posthog
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSOBFUSCATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest and analyze data from user survey responses and event properties (documented in references/09-surveys.md and references/01-event-capture.md). Because this data originates from untrusted external users, it could contain malicious instructions intended to manipulate the agent's logic during analysis.
- Ingestion points: Survey responses and event properties retrieved via the PostHog API.
- Boundary markers: The skill does not define specific delimiters or warnings to ignore embedded instructions in the processed data.
- Capability inventory: The skill utilizes REST API calls for data retrieval.
- Sanitization: No specific filtering or escaping mechanisms are recommended for processing these external inputs.
- [EXTERNAL_DOWNLOADS]: The maintenance script (scripts/check-updates.py) fetches package version data from PyPI (pypi.org). This targets an official and well-known service for integrity verification and does not involve remote code execution.
- [OBFUSCATION]: A standard minified JavaScript snippet is provided in references/00-overview.md for SDK initialization. This is a common performance optimization for a well-known analytics service and does not indicate malicious intent.
Audit Metadata