repo-to-video-ideas
Pass
Audited by Gen Agent Trust Hub on Oct 4, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were detected. The skill follows its stated purpose of scanning repository files for metadata and code patterns to generate content ideas. The workflow includes user confirmation before overwriting existing files, which is a good safety practice.
- [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests untrusted data from repository files (e.g., README.md, source code) to perform its analysis. However, given its restricted capabilities (writing a markdown file), the risk is minimal.
- Ingestion points: Files like
README.md,package.json, and source code are read in Step 1 of the workflow inSKILL.mdto identify project types and functionality. - Boundary markers: The skill instructions do not explicitly define boundary markers or warnings to the agent to ignore instructions within the analyzed files.
- Capability inventory: The skill has file-read capabilities and can create a directory and write a markdown file (
demo-video/video-ideas.md). - Sanitization: No specific sanitization or validation of the processed file content is mentioned.
Audit Metadata