gcp-cloud-functions
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- Command Execution (SAFE): The skill executes
gcloudcommands to deploy and manage serverless functions, which is consistent with its stated purpose. - Indirect Prompt Injection (SAFE): The Python code template for processing Pub/Sub messages creates a potential attack surface by logging unverified external data (
event['data']). This is a common pattern in basic examples but should be noted as a surface for indirect injection if an agent monitors these logs. - Ingestion points:
event['data']variable in theprocessfunction (SKILL.md). - Boundary markers: None present.
- Capability inventory: The skill allows function deployment and configuration via
gcloudCLI. - Sanitization: None provided in the snippet; data is decoded from Base64 and printed directly.
- Security Configuration (SAFE): Use of the
--allow-unauthenticatedflag in the deployment commands is a security best practice concern for the resulting deployment, but is not considered a malicious finding for the skill itself.
Audit Metadata