cloud-run-service-config
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides documentation, configuration templates, and guidance for Cloud Run services, which is consistent with its stated purpose.\n- [SAFE]: Shell command access is restricted to the
gcloudCLI within theallowed-toolsfrontmatter, following the principle of least privilege.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests user prompts to perform tasks with file-write and limited shell capabilities, representing a standard attack surface for agent skills.\n - Ingestion points: User requests triggering the skill via keywords like 'cloud run' or 'gcp' (SKILL.md).\n
- Boundary markers: None present in the instructions.\n
- Capability inventory:
Bash(gcloud:*),Write,Edit(SKILL.md).\n - Sanitization: No explicit sanitization or validation of user-provided parameters is defined.
Audit Metadata