topview-generate

Pass

Audited by Gen Agent Trust Hub on Jul 23, 2026

Risk Level: SAFEDATA_EXFILTRATIONPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [DATA_EXFILTRATION]: The skill manages authentication through a local credential file at ~/.topview/credentials.json. Access to this sensitive path is used by vendor scripts to store and retrieve API keys for communication with api.topview.ai.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests untrusted user assets and interpolates prompts into generation tasks without explicit boundary markers.
  • Ingestion points: Processes user-provided images, audio, and video via the scripts/shared/upload.py module and media generation tools.
  • Boundary markers: The prompt interpolation logic does not utilize delimiters to separate user data from system instructions.
  • Capability inventory: The skill possesses capabilities for media generation, file writes, and network operations to the vendor's API.
  • Sanitization: No explicit sanitization or safety filtering of user-supplied content was identified in the provided scripts.
  • [COMMAND_EXECUTION]: The skill includes Python scripts that perform network communication, file system operations, and local configuration management, wrapping the vendor's API functionality.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 23, 2026, 02:54 PM
Security Audit — agent-trust-hub — topview-generate