multi-agent-chat
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to read and interpret the contents of a shared file. This creates a vulnerability where malicious instructions embedded in the chat log by other agents or external processes could influence the agent's actions.
- [COMMAND_EXECUTION]: The skill utilizes shell commands including printf, wc, tail, and bash loops to manage the communication file and monitor it for new content.
Audit Metadata