sdd-verify

Pass

Audited by Gen Agent Trust Hub on Jul 7, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill identifies the verification surface by inspecting git diff. This creates an indirect prompt injection surface where malicious instructions embedded in code changes could potentially influence the agent's decision-making process during the detection phase.
  • Ingestion points: Git diff output used to detect Frontend vs API surfaces.
  • Boundary markers: Absent; no delimiters or warnings to ignore instructions within the diff are provided.
  • Capability inventory: Shell execution (npx playwright test, dev server start), file system writes (scripts-dev/api_smoke.spec.ts).
  • Sanitization: Absent; the skill does not mention filtering or escaping the diff content.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands to start development servers and run Playwright tests. It also involves creating and running temporary test scripts under the scripts-dev/ directory.
  • [EXTERNAL_DOWNLOADS]: The skill suggests installing the @playwright/test package using pnpm if it is missing. This is a standard dependency from the well-known NPM registry.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 7, 2026, 04:19 AM
Security Audit — agent-trust-hub — sdd-verify