gws-modelarmor-sanitize-prompt
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because it processes untrusted data provided by the user.
- Ingestion points: Untrusted input is ingested via the --text and --json flags, or through standard input (SKILL.md).
- Boundary markers: No specific delimiters or boundary instructions are defined to separate user input from the command instructions.
- Capability inventory: The skill is designed to execute the gws CLI tool.
- Sanitization: The primary purpose of the skill is to sanitize input using Google Model Armor templates, which acts as a mitigation against malicious content.
- [COMMAND_EXECUTION]: The skill instructions define the execution of the gws binary to perform sanitization tasks.
- Evidence: The skill defines the usage of gws modelarmor +sanitize-prompt with various parameters.
Audit Metadata