CI/CD Validation & Merge Workflow

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill provides legitimate instructions for project maintenance, including code formatting, linting, and testing. All documented commands are standard for Rust development environments.
  • [COMMAND_EXECUTION]: The workflow relies on shell command execution for its primary functions, including repository management (git), build automation (cargo), and GitHub interaction (gh). It also involves executing a local validation script (./scripts/ci/validate-cleanup.sh) to automate pre-push checks.
  • [PROMPT_INJECTION]: The skill defines workflows that involve reading external content, such as pull request descriptions and CI logs, which introduces a surface for indirect prompt injection.
  • Ingestion points: gh pr view and gh run view --log are used in SKILL.md and merge-process.md to retrieve external data from GitHub.
  • Boundary markers: Absent; the instructions do not specify the use of delimiters or warnings to isolate external data from core instructions.
  • Capability inventory: The agent has the ability to compile code, execute tests, and modify repository state through merging pull requests.
  • Sanitization: No explicit sanitization or validation of the content retrieved from GitHub is mentioned in the instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 07:21 PM
Security Audit — agent-trust-hub — CI/CD Validation & Merge Workflow