video-to-gif
Fail
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: HIGHCREDENTIALS_UNSAFECOMMAND_EXECUTION
Full Analysis
- [CREDENTIALS_UNSAFE]: The skill requests explicit permission to read
~/.meitu/credentials.jsonto retrieve authentication keys (MEITU_OPENAPI_ACCESS_KEYandMEITU_OPENAPI_SECRET_KEY). Accessing credential stores in the user's home directory is a high-sensitivity operation. - [COMMAND_EXECUTION]: The core workflow involves executing the
meituCLI with parameters such as{video_url}and{content_description}interpolated directly into a shell command string. The absence of visible sanitization or shell-escaping for these inputs creates a command injection vulnerability where a maliciously crafted URL or prompt could execute arbitrary code.
Recommendations
- AI detected serious security threats
Audit Metadata