discord-clawd
Pass
Audited by Gen Agent Trust Hub on May 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions direct the agent to execute local Python scripts located in the user's Projects directory using shell commands such as
python3 skills/openclaw-relay/scripts/openclaw_relay.py. - [PROMPT_INJECTION]: The skill acts as a message proxy, creating an indirect prompt injection surface.
- Ingestion points: User-provided message content is ingested and passed to the relay script via the
--messageargument. - Boundary markers: No delimiters or ignore-instructions markers are used to encapsulate the user-provided content.
- Capability inventory: The skill utilizes shell command execution via Python.
- Sanitization: There are no instructions for the agent to sanitize or escape user input before it is interpolated into the shell command string.
Audit Metadata