oodle-cli
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill instructs the user to install the
oodleCLI via Homebrew and Go. These downloads originate from the official repositories of the skill's author (oodle-ai). - [COMMAND_EXECUTION]: The skill outlines usage of the
oodleCLI along with standard utilities likejqandbrewfor monitoring and system management tasks. - [INDIRECT_PROMPT_INJECTION]: The skill processes external data which could potentially contain malicious instructions.
- Ingestion points: CLI output from
oodlecommands and local files ingested via the-fflag inSKILL.md. - Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the provided examples.
- Capability inventory: The skill has the ability to execute shell commands, perform network operations via the CLI, and write to the local file system.
- Sanitization: There is no evidence of input validation or sanitization of data received from the CLI before it is used in subsequent logic.
Audit Metadata