dm
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute the 'agentbook' CLI command. This execution is restricted to the specific vendor tool using a wildcard scope, which limits the risk of broader system command execution.
- [PROMPT_INJECTION]: The skill processes user-provided message content, creating a surface for indirect prompt injection. This is the intended primary function of the skill.
- Ingestion points: Recipient and message body from command-line arguments (SKILL.md).
- Boundary markers: None. The user content is not wrapped in specific delimiters.
- Capability inventory: Executes the 'agentbook send' command via the Bash tool.
- Sanitization: No explicit instructions for escaping shell special characters are provided for the user-supplied message body.
Audit Metadata