lov-media-crawler
Warn
Audited by Gen Agent Trust Hub on Nov 17, 2026
Risk Level: MEDIUMPRIVILEGE_ESCALATIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PRIVILEGE_ESCALATION]: The skill facilitates the execution of scripts that require administrative privileges to modify system-level configurations.
- Evidence:
scripts/wxclient.shusessudoto run thewx_video_downloadbinary, which is designed to install a root certificate and configure a system-wide proxy. - [EXTERNAL_DOWNLOADS]: Setup routines fetch code and pre-compiled binaries from non-whitelisted third-party GitHub repositories.
- Evidence:
scripts/media_crawler.pydownloads a macOS binary fromgithub.com/ltaoo/wx_channels_downloadand clones a code repository fromgithub.com/NanmiCoder/MediaCrawler. - [DYNAMIC_EXECUTION]: The tool assembles and executes Python code dynamically to inject configuration into external crawler components at runtime.
- Evidence:
scripts/media_crawler.pyconstructs a Python script string and executes it viauv run python -cto initiate the MediaCrawler adapter with specific configuration overrides. - [COMMAND_EXECUTION]: Extensive use of shell commands to manage system credentials, external dependencies, and file system operations.
- Evidence: The implementation uses
subprocess.runto interact with the macOS Keychain (securitytool),git,uv, and various download utilities likearia2candcurl. - [DATA_EXFILTRATION]: Provides functionality to transmit data to an external, third-party resolution service.
- Evidence: The skill defines and utilizes
https://sph.litao.workers.dev/api/fetch_video_profileas a remote resolver when the--allow-public-resolverflag is enabled. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted metadata from external social media platforms which directly influences file system write paths.
- Ingestion points: The
feed_metadataandwxclient_metadatafunctions inscripts/media_crawler.pyextract titles and descriptions from social media API responses. - Boundary markers: Absent; there are no instructions to the agent to ignore embedded commands in the metadata.
- Capability inventory: The skill has the capability to write to the file system via the
destination_pathandrun_downloaderfunctions. - Sanitization: Employs a
safe_filenameregex-based filter to strip restricted characters from strings before using them in file paths.
Audit Metadata