customer-360
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
composioCLI to interact with external support and CRM services. It passes user-provided identifiers from the$ARGUMENTSvariable directly into shell commands for tool execution. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the
$ARGUMENTSparameter. 1. Ingestion points: User-provided email or name via the$ARGUMENTSvariable in SKILL.md. 2. Boundary markers: Absent; the user input is interpolated into the workflow without delimiters or instructions to ignore embedded commands. 3. Capability inventory: Execution ofcomposioCLI commands which can perform read/write operations against integrated services in SKILL.md. 4. Sanitization: Absent; there is no defined validation or escaping of the customer identifier before it is used to filter queries.
Audit Metadata