agent-message-cli
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from external sources, creating a risk for indirect prompt injection attacks.
- Ingestion points: The
readandwatchcommands retrieve message history and real-time streams from an external server (SKILL.md). - Boundary markers: The skill instructions do not provide delimiters or specific guidance to the agent on how to treat content from external messages as data rather than instructions.
- Capability inventory: The agent has the ability to send messages, manage configurations (including server URLs), and perform account-related operations (SKILL.md).
- Sanitization: No sanitization or validation steps are defined for processing the content of received messages.
Audit Metadata