video-downloader
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The analyzed content consists entirely of descriptive Markdown and usage examples. No executable code, shell commands, or configuration files are present.
- [SAFE]: No malicious patterns such as direct prompt injection, credential theft, or obfuscation were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external content from video platforms. This represents an inherent risk surface for indirect prompt injection via untrusted metadata (titles/descriptions), though no active exploitation is present in the skill definition. 1. Ingestion points: External URLs and video metadata (SKILL.md). 2. Boundary markers: Absent in the provided instructions. 3. Capability inventory: File system writes to user directories (described in examples). 4. Sanitization: Not specified in the documentation.
Audit Metadata