agent-channeltalkbot
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it reads and processes data from external Channel Talk chat sessions.
- Ingestion points: Data enters the agent's context through
snapshot,message list, andchat listcommands as described inSKILL.mdandreferences/common-patterns.md. - Boundary markers: There are no instructions requiring the agent to wrap untrusted chat content in delimiters or to ignore embedded instructions within processed messages.
- Capability inventory: The agent has access to
Bash(agent-channeltalkbot:*), which includes tools for sending messages, creating/deleting bots, and closing conversations. - Sanitization: No sanitization or validation of external message content is performed before the data is presented to the agent.
Audit Metadata