ci-cd-automation
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a safety-oriented guidance document for CI/CD tasks, incorporating defensive instructions such as prohibited secret storage and mandatory human approval gates for high-risk actions.
- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion and modification of repository content, including CI/CD workflow files and scripts, which are external data sources.
- Ingestion points: The agent is instructed to inspect existing CI workflow files, repository scripts, and lockfiles as defined in references/current-guidance.md.
- Boundary markers: The skill includes explicit "Stop If" and "Verification" sections that provide clear delimiters and stop conditions for agent actions.
- Capability inventory: The skill enables the agent to modify repository workflows, deployment scripts, and package publishing configurations.
- Sanitization: Instructions mandate that high-impact operations like deployment or publishing remain behind explicit environments, protected branches, and human approval gates.
Audit Metadata