build-workspace-docs
Pass
Audited by Gen Agent Trust Hub on Sep 18, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill uses
npxto run theai-agent-skillspackage, which involves fetching the package from the npm registry. - [COMMAND_EXECUTION]: Executes shell commands such as
npx ai-agent-skills build-docsto manage workspace files and verify synchronization. - [INDIRECT_PROMPT_INJECTION]: The skill processes workspace files and skill metadata to regenerate documentation sections.
- Ingestion points: Reads data from
README.md,WORK_AREAS.md, and skill catalog metadata (referenced inSKILL.md). - Boundary markers: Utilizes
<!-- GENERATED:...:start/end -->markers to identify managed sections. - Capability inventory: Executes shell commands via
npxand writes updates to workspace files (referenced inSKILL.md). - Sanitization: No explicit sanitization or filtering logic for processed metadata is defined within the skill instructions.
Audit Metadata