arkweb-design-alignment

Pass

Audited by Gen Agent Trust Hub on Aug 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill's primary function is to synchronize code and design documentation. All modifications to files or code generation requests are gated by a mandatory user-confirmation step via the AskUserQuestion tool, which serves as a critical security control to prevent unauthorized changes.
  • [COMMAND_EXECUTION]: The skill utilizes the Grep utility in Step 1 to perform targeted searches within the implementation code directory. This is used for identifying class definitions, API signatures, and data structures to facilitate comparison with design documents.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes untrusted documentation and source code files.
  • Ingestion points: Documentation files (requirement.md, design.md, spec.md, analysis.md) and source code files within the {WORK_HOME} directory (Step 1).
  • Boundary markers: The instructions do not define specific delimiters or warnings to ignore instructions embedded within the ingested data.
  • Capability inventory: The skill can read/search files (Grep, Read), modify design documentation (Edit), and delegate code generation tasks to the arkweb-coder sub-agent (Step 4).
  • Sanitization: There is no evidence of filtering or sanitization of content extracted from documents before it is used for documentation updates or coder instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 8, 2026, 09:00 AM
Security Audit — agent-trust-hub — arkweb-design-alignment