backend-to-frontend-handoff-docs

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is designed to perform local file system operations, specifically creating and updating documentation files within the .claude/docs/ai/ directory. This is consistent with its stated purpose of generating versioned API handoff documentation.
  • [PROMPT_INJECTION]: The instructions include a "No Chat Output" directive, which commands the agent to suppress all discussion and explanation. While used here as a functional constraint for clean file generation, this is a known technique for suppressing safety warnings or secondary actions in adversarial contexts.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it processes external, potentially untrusted data (source code and business context) to generate its output.
  • Ingestion points: The skill analyzes completed API code, including endpoints, controllers, services, and DTOs.
  • Boundary markers: There are no explicit instructions to use delimiters or ignore embedded instructions within the source code being analyzed.
  • Capability inventory: The skill possesses the capability to write and version files in the local filesystem (SKILL.md).
  • Sanitization: No sanitization or validation of the ingested code or context is specified before it is interpolated into the handoff document template.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 01:27 PM
Security Audit — agent-trust-hub — backend-to-frontend-handoff-docs