gallery-dl
Warn
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONDATA_EXFILTRATIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches the application binary from its official GitHub repository.
- [REMOTE_CODE_EXECUTION]: The installation instructions include downloading a binary file from a remote source and executing it after modifying permissions.
- [DYNAMIC_EXECUTION]: The skill documents the use of the 'exec' post-processor in the JSON configuration, which allows for the execution of arbitrary shell commands (e.g., ImageMagick's 'convert') on the file paths of downloaded media.
- [DATA_EXFILTRATION]: Includes instructions for the '--cookies-from-browser' feature, which enables the tool to read sensitive session cookies and authentication data from the user's local Firefox or Chrome profiles.
- [PRIVILEGE_ESCALATION]: Recommends the use of 'chmod +x' to grant execution permissions to a binary downloaded from an external network source.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill is designed to ingest and process data from a wide variety of external, untrusted social media and image hosting URLs.
- Boundary markers: No specific boundary markers or 'ignore' instructions for embedded data are provided to the agent.
- Capability inventory: The skill possesses file-writing capabilities, network access for data retrieval, and the ability to execute shell commands via configured post-processors.
- Sanitization: No explicit content sanitization or validation of the remote data is described in the provided instructions.
Audit Metadata