product-discovery
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to download and install the channel3 CLI tool from the vendor's GitHub repository and a Homebrew tap.
- [COMMAND_EXECUTION]: The skill operates by executing shell commands using the channel3 CLI to perform product, category, and brand searches.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted product descriptions and metadata from an external catalog, which serves as a potential surface for instructions intended to influence the agent.
- Ingestion points: Product titles, descriptions, and attributes retrieved via the channel3 CLI in SKILL.md.
- Boundary markers: The skill lacks explicit delimiters or instructions to ignore embedded commands in the retrieved data.
- Capability inventory: The agent has permissions for shell command execution and network access as defined in skill.yaml.
- Sanitization: There are no specified sanitization or validation steps for the content returned by the external service.
Audit Metadata