skills-store
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill is designed to fetch and execute external scripts from a shared PostHog repository using the
posthog:skill-file-gettool. This is the intended primary function for managing team-shared resources. - [INDIRECT_PROMPT_INJECTION]: The skill establishes a workflow where external instruction bodies are retrieved and treated as system-level directives. This creates a surface for indirect prompt injection if malicious content is stored in the shared team repository.
- [COMMAND_EXECUTION]: The skill utilizes a comprehensive set of MCP tools (
posthog:skill-*) to perform management operations such as creating, updating, and archiving remote skill definitions.
Audit Metadata