X Chat
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires downloading a helper repository from the X development platform's GitHub organization and installing the
chatxdkpackage from PyPI. - [COMMAND_EXECUTION]: Local shell commands are used to manage encryption and decryption through a helper script, utilizing variable interpolation for user IDs and file paths.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted text from X DMs which could contain malicious instructions. While the instructions include a safety section to mitigate this, the attack surface remains.
- Ingestion points: Message content is retrieved via the
get_chat_conversation_eventstool. - Boundary markers: The skill contains explicit instructions to treat inbound text as untrusted data rather than instructions.
- Capability inventory: The skill can execute shell commands, perform network operations via the X MCP, and manage local files.
- Sanitization: The skill relies on model-level instructions to ignore embedded commands in decrypted text.
- [DYNAMIC_EXECUTION]: The skill executes a downloaded Python script (
xchat_lite.py) to perform cryptographic operations on-the-fly.
Audit Metadata