windsurf-cicd-github-actions

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill assists in managing CI/CD workflows by reading and writing files within the .github/workflows/ and .windsurf/cicd/ directories. This introduces a potential surface for indirect prompt injection if the processed repository content contains malicious instructions designed to manipulate the agent.
  • Ingestion points: Project configuration files, GitHub Actions YAML files, and templates within the project root.
  • Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill is granted access to powerful tools including Bash(cmd:*), Read, Write, and Edit, which could be abused if an injection is successful.
  • Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the workflow files before execution or modification.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — windsurf-cicd-github-actions