cloud-run
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the gcloud CLI to perform operations on Google Cloud Run. This involves executing shell commands to manage services, jobs, and domain mappings.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could potentially contain malicious instructions intended to mislead the AI agent.
- Ingestion points: The skill reads external data through 'gcloud run logs read' and 'gcloud run replace' commands in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potential commands embedded within logs or YAML files.
- Capability inventory: The skill has high-impact capabilities including modifying IAM policies ('add-iam-policy-binding'), deleting services, and updating configurations.
- Sanitization: No sanitization, validation, or escaping of ingested data is described in the skill instructions.
Audit Metadata