google-trends-research
Pass
Audited by Gen Agent Trust Hub on Oct 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the vendor-specific postplus CLI to execute research commands such as google-trends-fast as described in the SKILL.md execution examples.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided keywords which creates a surface for indirect prompt injection when these terms are passed to the CLI tool.
- Ingestion points: User-supplied terms for the --query and --country flags in SKILL.md.
- Boundary markers: None; the skill does not use delimiters to separate untrusted user input from the command structure.
- Capability inventory: The skill has the capability to execute subprocesses via the postplus research run command.
- Sanitization: There is no evidence of input sanitization or escaping for the query strings before they are interpolated into the shell command.
Audit Metadata