samsung-smart-tv
Warn
Audited by Gen Agent Trust Hub on Mar 21, 2026
Risk Level: MEDIUMCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The script
scripts/setup_smartthings.pyexecutes the SmartThings CLI usingsubprocess.runto manage OAuth applications and query device lists. - [EXTERNAL_DOWNLOADS]: The skill fetches the
@smartthings/clipackage from the npm registry at runtime usingnpxif the command is not natively present on the system. - [CREDENTIALS_UNSAFE]: The script provides the Personal Access Token (PAT) to the CLI via the
--tokencommand-line argument. This allows the secret to be visible to other users or monitoring processes on the same host through the process table. - [DATA_EXFILTRATION]: The default OAuth redirect URI is configured as
https://httpbin.org/get. This configuration transmits sensitive authorization codes to an external third-party debugging service. - [PROMPT_INJECTION]: The skill ingests and parses JSON data from external CLI tool outputs which could be susceptible to manipulation if the local environment is compromised.
- Ingestion points:
scripts/setup_smartthings.pyparses output fromsmartthingsCLI commands. - Boundary markers: None present.
- Capability inventory: The skill can execute subprocesses and write secrets to the local
~/.clawdbot/.envfile. - Sanitization: No specific validation or sanitization of CLI output is performed prior to processing.
Audit Metadata