openai-api

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/check-versions.sh executes shell commands including npm list and npm view to verify package versions against the npm registry.
  • [INDIRECT_PROMPT_INJECTION]: The skill templates, particularly templates/cloudflare-worker.ts and templates/structured-output.ts, are vulnerable to indirect prompt injection due to lack of input protection.
  • Ingestion points: User-provided strings are ingested via the message parameter in templates/cloudflare-worker.ts and the texts array in templates/structured-output.ts.
  • Boundary markers: Absent. The templates interpolate user input directly into the messages array of the OpenAI API call without using delimiters or system-level instructions to ignore embedded commands.
  • Capability inventory: The skill uses fetch to communicate with the OpenAI API and includes scripts that can write files to the local system (e.g., fs.writeFileSync in multiple templates).
  • Sanitization: Absent. There is no evidence of input validation, escaping, or filtering of user-provided content before it is sent to external LLM endpoints.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — openai-api