getnote-tag
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to interact with the local environment by executing the
getnoteCLI tool. It defines specific subcommands for listing, adding, and removing tags (getnote tag list,getnote tag add,getnote tag remove). - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect injection as it processes external identifiers and labels and interpolates them into shell commands.
- Ingestion points: User-provided note identifiers, tag names, and tag IDs are used as arguments for the CLI tool (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or escaping mechanisms for the interpolated shell arguments.
- Capability inventory: The skill possesses the capability to execute shell commands via the
getnotetool (SKILL.md). - Sanitization: The instructions explicitly state that note IDs and tag IDs should be passed "as-is" as strings, which relies on the agent platform's underlying shell execution safety.
Audit Metadata