image-face-swap

Pass

Audited by Gen Agent Trust Hub on Jun 22, 2026

Risk Level: SAFEDATA_EXFILTRATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
  • [DATA_EXFILTRATION]: Transmits user-provided face images and scene images to the external Meitu OpenAPI for processing.
  • [EXTERNAL_DOWNLOADS]: Downloads and installs the meitu-cli tool from the npm registry if not present or outdated.
  • [COMMAND_EXECUTION]: Executes the meitu command-line interface to interact with the Meitu API.
  • [CREDENTIALS_UNSAFE]: Accesses sensitive API credentials stored in ~/.meitu/credentials.json or environment variables for authentication with the Meitu service.
  • [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection as it processes untrusted external data that could contain instructions designed to manipulate the agent.
  • Ingestion points: Data enters the context via the head_image_url, sence_image_url, and prompt parameters.
  • Boundary markers: No explicit delimiters or boundary instructions are used to isolate the external inputs.
  • Capability inventory: The skill executes the meitu CLI and writes resulting files to the local filesystem.
  • Sanitization: No validation or filtering is performed on the input prompt or external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 22, 2026, 04:39 AM
Security Audit — agent-trust-hub — image-face-swap