video-downloader
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill provides instructions for the agent to ingest data from external platforms which can serve as a vector for malicious content.\n
- Ingestion points: The agent is instructed to fetch and process video metadata and descriptions from external URLs provided in
SKILL.md.\n - Boundary markers: The skill does not define any delimiters or safety instructions to help the agent distinguish between its core instructions and potentially adversarial content within video metadata.\n
- Capability inventory: The skill possesses the capability to write files to the local file system (specifically
~/Downloads/) based on external content, as described inSKILL.md.\n - Sanitization: No sanitization or validation protocols are specified for the data retrieved from remote sources.\n- [NO_CODE]: The skill submission consists only of informational markdown and documentation without any source code, scripts, or binaries to analyze for technical vulnerabilities.
Audit Metadata