create-pipeline-v1

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to take natural language requirements from a user and translate them into Harness Pipeline YAML, which can then be pushed to a live environment using the harness_create tool. This workflow is vulnerable to indirect prompt injection if the user provides malicious requirements intended to inject unauthorized commands or exfiltration scripts into the resulting pipeline.
  • Ingestion points: User-provided descriptions of the pipeline (CI/CD logic, build scripts, deployment targets) processed by the agent as described in the instructions section of SKILL.md.
  • Boundary markers: The instructions do not define specific delimiters or guardrails to prevent the agent from obeying instructions embedded within the user's requirement description.
  • Capability inventory: The skill possesses the capability to create resources in the Harness platform via the harness_create MCP tool, which executes the generated YAML configuration.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the generated YAML against a security policy before invoking the deployment tool.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:25 PM
Security Audit — agent-trust-hub — create-pipeline-v1