code-quality-setup
Pass
Audited by Gen Agent Trust Hub on Apr 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute multiple package managers (npm, pip, go, cargo, dotnet) and code quality CLI tools (such as ruff, golangci-lint, clang-tidy, and trivy) to configure and audit the repository. It also uses sudo for privilege escalation when required for tool installation.- [EXTERNAL_DOWNLOADS]: Directs the agent to globally install several utility packages from the NPM registry, including compose-agentsmd, task-tracker, and thread-inbox, ensuring the necessary environment for the vendor's workflow.- [REMOTE_CODE_EXECUTION]: The skill utilizes the compose-agentsmd tool to fetch and synchronize agent instructions from a remote GitHub repository (github:metyatech/agent-rules). This mechanism allows the agent's operating rules to be updated dynamically from an external source at runtime.- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted repository content (source code and manifests) to perform its setup tasks without explicit sanitization or instruction boundaries.
- Ingestion points: The agent reads the entire repository's file structure, including code comments and configuration files.
- Boundary markers: Absent; there are no specified delimiters to prevent the agent from following instructions embedded within the processed data.
- Capability inventory: The agent has the authority to write configuration files, install new dependencies, and execute shell commands.
- Sanitization: No logic is provided to validate or escape external repository content before the agent acts upon it.
Audit Metadata