wewrite-visual
Pass
Audited by Gen Agent Trust Hub on Jul 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the Bash tool to execute various subcommands of the
wewriteCLI, such aswewrite diagnose,wewrite home, andwewrite image-gen. These commands are used for system diagnostics, environment discovery, and image generation. - [EXTERNAL_DOWNLOADS]: The instructions guide the agent to suggest installing the
wewriteutility viauv tool install wewriteor a localinstall.shscript if the command is missing. This represents a functional dependency on a vendor-provided tool. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the processing of untrusted article data. * Ingestion points: The article content is read from
{home}/output/article.md. * Boundary markers: The instructions do not implement delimiters or safety instructions to prevent the agent from following directions potentially embedded in the source article. * Capability inventory: The skill possesses capabilities to write to the file system and execute shell commands via Bash. * Sanitization: No content sanitization or validation is applied to the ingested article text prior to prompt interpolation.
Audit Metadata