The Agent Skills Directory

[SAFE]: The skill facilitates standard debugging operations for Harness pipelines. It uses a series of MCP tools (harness_diagnose, harness_status, etc.) to retrieve telemetry and configuration data necessary for troubleshooting failures.
[DATA_EXPOSURE]: The skill instructions involve fetching pipeline logs and YAML definitions. While these resources may contain sensitive information about a user's build environment, accessing them is required for the skill's primary function (diagnosing build failures). No unauthorized exfiltration or hardcoded credentials were identified.
[SAFE]: No evidence of prompt injection, obfuscation, persistence mechanisms, or unauthorized privilege escalation was found in the skill instructions or metadata.

debug-pipeline