pipeline-triage
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXFILTRATION]: The skill manages Bruin Cloud credentials and pipeline metadata. It explicitly mandates secure credential handling, advising users to use environment variables (BRUIN_CLOUD_API_KEY) or interactive authentication (bruin cloud login) rather than passing secrets as command-line arguments.
- [COMMAND_EXECUTION]: The skill utilizes the bruin CLI and git for operational tasks. All commands (e.g., bruin cloud runs list, git log) are directly related to the skill's primary function of triaging pipeline issues and do not involve arbitrary or unsafe command construction.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests external data from Bruin Cloud responses and Git commit history. This presents a potential surface for indirect prompt injection if malicious content is embedded in run logs or commit messages; however, the skill's restricted scope as a read-only dispatcher minimizes the impact of such attacks.
- [EXTERNAL_DOWNLOADS]: The skill references the installation of additional skills via bruin ai skills all. This is a standard feature of the Bruin ecosystem provided by the vendor and is used for its intended purpose of extending the agent's capabilities.
Audit Metadata