contacts
Pass
Audited by Gen Agent Trust Hub on Mar 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions rely on executing the
larkCLI tool to perform various administrative and lookup tasks, such aslark contact get,lark contact search, andlark auth login. - [PROMPT_INJECTION]: There is a potential for indirect prompt injection as the skill retrieves and processes data from an external source (the Lark API).
- Ingestion points: Employee names, job titles, and department descriptions retrieved via search and get commands in
SKILL.md. - Boundary markers: Absent. The instructions do not specify any delimiters or warnings to the agent to ignore potential instructions embedded in the retrieved JSON data.
- Capability inventory: The skill allows for local shell command execution via the
larkCLI tool. - Sanitization: Absent. There is no evidence of filtering or validation of the data returned by the API before it is processed by the agent.
Audit Metadata