ddd-architecture-evaluator
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill evaluates project-specific information and architectural documentation provided by the user, creating a surface for untrusted data ingestion into the agent's context.\n
- Ingestion points: The Workflow section in SKILL.md specifies that the agent should evaluate project background, architecture documentation, and code structure provided by the user.\n
- Boundary markers: Absent; there are no instructions to use delimiters or ignore embedded instructions within the user-provided data.\n
- Capability inventory: The skill is strictly documentation-based and does not include tools for command execution, file system modifications, or network communication.\n
- Sanitization: Absent; no escaping or filtering of external content is defined in the instructions.\n- [NO_CODE]: The skill consists exclusively of Markdown documentation, templates, and YAML configuration. No Python, Node.js, shell scripts, or binary files are present in the package, eliminating the risk of direct malicious code execution.
Audit Metadata