Skills
Navigate
skills/posthog/skills/installing-posthog-from-chat/Gen Agent Trust Hub

installing-posthog-from-chat

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill architecture allows for untrusted data from an external API to be injected into the agent's conversation flow.
  • Ingestion points: Untrusted content enters the context via the wizard-install-status tool, specifically through the next_step, tasks, and error_message response fields as defined in SKILL.md.
  • Boundary markers: There are no boundary markers or instructions to treat the external content as data rather than instructions. The instructions in SKILL.md explicitly direct the agent to relay the next_step field "as is."
  • Capability inventory: The skill possesses capabilities to list and retrieve GitHub repositories through integrations and initiate/monitor cloud-based installation runs (all defined in SKILL.md).
  • Sanitization: No sanitization, escaping, or schema validation is performed on the messages retrieved from the PostHog API before they are processed or displayed to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 10:13 PM