port-registry

Pass

Audited by Gen Agent Trust Hub on Mar 27, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from untrusted sources without explicit boundary markers or sanitization.
  • Ingestion points: Reads project configuration files such as package.json and vite.config.ts, as well as a local registry file at ~/.config/port-registry.json.
  • Boundary markers: The instructions do not define delimiters or specific safety instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill involves reading and writing configuration files on the local filesystem.
  • Sanitization: No evidence of content validation or escaping is present for the data retrieved from the files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 27, 2026, 01:25 AM