configure-repo-scan
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
harness_getMCP tool to retrieve current pipeline YAML configurations and theharness_updatetool to commit structural changes to the pipeline execution logic. - [SAFE]: All external URL references and help documentation links point to official Harness domains (harness.io).
- [PROMPT_INJECTION]: 1. Ingestion points: The skill ingests untrusted YAML configuration data from existing pipelines via the
harness_gettool inSKILL.md. 2. Boundary markers: No explicit delimiters or 'ignore' instructions are used when processing the retrieved YAML. 3. Capability inventory: The skill includes the capability to modify and overwrite pipeline configurations using theharness_updatetool inSKILL.md. 4. Sanitization: The skill relies on hardcoded YAML templates for scanner steps, ensuring that the inserted content follows a strict schema and reducing the risk of malicious payload injection.
Audit Metadata