create-pipeline

Pass

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes local codebase files to auto-detect build and deployment configurations, creating a surface where malicious strings in project files could attempt to influence the generated pipeline instructions.
  • Ingestion points: Project configuration files (e.g., package.json, go.mod, pom.xml) and deployment manifests are read and processed as described in references/codebase-analysis.md.
  • Boundary markers: The instructions do not define specific delimiters or instructions to the model to ignore embedded commands within the analyzed files.
  • Capability inventory: The skill uses MCP tools (harness_create, harness_update) to write and modify pipeline configurations.
  • Sanitization: The skill mitigates risk by requiring user clarification of detected settings before generation and mandating YAML validation.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 18, 2026, 11:25 PM
Security Audit — agent-trust-hub — create-pipeline