api-endpoint-builder

Pass

Audited by Gen Agent Trust Hub on Jun 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection in scripts/generate_endpoints.py. User-provided API descriptions are interpolated into LLM prompts without delimiters or sanitization, potentially allowing an attacker to influence the generated code content.
  • Ingestion points: The description positional argument in scripts/generate_endpoints.py is the primary entry point for untrusted data.
  • Boundary markers: No delimiters or "ignore instructions" warnings are used in the prompt templates.
  • Capability inventory: The script has the capability to write files to the local filesystem using Path.write_text within the write_files function.
  • Sanitization: The script does not validate the generated code content or the requested file paths beyond minimal cleaning.
  • [COMMAND_EXECUTION]: The skill's workflow involves generating and writing executable source files (e.g., API routes and routers) to the disk. The write_files function lacks robust path traversal validation (it only strips leading slashes), which could be combined with prompt injection to write files to unauthorized or sensitive locations on the system.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 27, 2026, 02:53 PM
Security Audit — agent-trust-hub — api-endpoint-builder