firewall-rule-generator
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes natural language user requests to generate cloud configurations and execute management commands, which creates an inherent attack surface for indirect prompt injection.\n
- Ingestion points: Processes user prompts for firewall rule generation as defined in the activation triggers and overview section of SKILL.md.\n
- Boundary markers: The instructions do not specify the use of delimiters or specific isolation markers to separate user-provided data from execution logic.\n
- Capability inventory: The skill is configured to utilize tools such as Write, Edit, and Bash(gcloud:*) to modify configurations and perform infrastructure tasks.\n
- Sanitization: The instructions mention validating outputs against standards, but no explicit sanitization or filtering logic is defined for the incoming user-provided prompts.\n- [NO_CODE]: The skill consists solely of a documentation and configuration file (SKILL.md) and does not include any accompanying scripts, binaries, or executable code.
Audit Metadata