harness-pipeline
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources, creating a surface for potential instruction injection.
- Ingestion points: Data is ingested from Harness pipeline execution logs (via the
logsaction) and Jira issue statuses (during thetriggeraction). - Boundary markers: The skill does not define specific delimiters or instructional warnings to prevent the agent from obeying instructions that might be embedded in the external logs or Jira comments.
- Capability inventory: The skill has permissions to trigger pipeline executions through the Harness REST API and to modify Jira issue comments and statuses.
- Sanitization: No validation, filtering, or sanitization processes are described for the data retrieved from external CI/CD or issue tracking systems.
Audit Metadata