github-social-preview
Pass
Audited by Gen Agent Trust Hub on Jul 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes a local script (
scripts/generate_preview.py) to process image generation and compression logic. - [EXTERNAL_DOWNLOADS]: Retrieves repository metadata and README files from
github.comandraw.githubusercontent.com. - [PROMPT_INJECTION]: The skill handles untrusted data from external repositories that is passed into a shell command context.
- Ingestion points: Repository name, description, and README content fetched via
WebFetchinSKILL.md. - Boundary markers: Not present; instructions do not define delimiters for external content.
- Capability inventory: Shell execution of the local Python script
scripts/generate_preview.pyas described inSKILL.md. - Sanitization: Metadata is not explicitly escaped or validated before use as a command argument.
Audit Metadata