cloud-run-service-config
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [Indirect Prompt Injection] (LOW): The skill possesses a vulnerability surface for indirect prompt injection. 1. Ingestion points: User requests processed by the agent. 2. Boundary markers: Absent; no instructions provided to ignore instructions within user-provided data. 3. Capability inventory: Bash(gcloud:*), Read, Write, and Edit tools (specified in metadata). 4. Sanitization: Absent; no validation or escaping of user input is defined for tool arguments.
- [Command Execution] (SAFE): The skill requests Bash permissions for the gcloud utility. This is consistent with its stated purpose for GCP configuration and no malicious command strings are included in the skill body.
- [Prompt Injection] (SAFE): No instructions were found that attempt to bypass AI safety filters or override system instructions.
Audit Metadata