deployment-composer

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Executes shell commands via git, gh, npm, bun, and npx to perform repository discovery, run quality gates, and trigger deployments based on local configuration scripts.
  • [PROMPT_INJECTION]: Vulnerable to indirect prompt injection due to repository data ingestion.
  • Ingestion points: Reads local configuration and workflow files (package.json, vercel.json, .github/workflows) via cat, find, and rg (SKILL.md).
  • Boundary markers: Lacks clear delimiters or instructions to ignore embedded prompts in the repository files it processes.
  • Capability inventory: Executes a variety of shell commands and interacts with GitHub via git and gh tools (SKILL.md).
  • Sanitization: No evidence of validation or sanitization for content read from repository files before it influences orchestration decisions.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — deployment-composer