gcp-auth
Pass
Audited by Gen Agent Trust Hub on Sep 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONMETADATA_POISONING
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions provide templates for CLI commands that process external data such as project IDs and service account emails.
- Ingestion points: Variable placeholders like
my-project,alice@example.com, andprod-deploy@my-project.iam.gserviceaccount.comthroughoutSKILL.md. - Boundary markers: No explicit delimiters or instructions are provided to the agent to treat these interpolated values as untrusted data.
- Capability inventory: The instructions involve high-privilege command execution via the
gcloudCLI, including IAM policy modifications (gcloud iam service-accounts add-iam-policy-binding). - Sanitization: No sanitization or validation logic is defined for the variables before they are used in shell commands.
- [METADATA_POISONING]: The
authorfield in the skill's metadata is set togoogle-cloud, which is a trusted organization, while the skill's actual author context isterminalskills. This discrepancy in author identification can lead to incorrect assumptions regarding the official status or provenance of the skill.
Audit Metadata