docgen
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes repository-local scripts
scripts/generate-usage-docs.mjsandscripts/check-usage-docs-sync.sh. These scripts are part of the project environment and are used to process source files and generate output documents. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it reads project source files and skill definitions to extract documentation content.
- Ingestion points: Project source files and directories specified in the configuration (e.g.,
skills/commands/,cli/src/commands/). - Boundary markers: None identified in the instructions.
- Capability inventory: Uses
Read,Write,Grep,Glob, andBash(*)tools. - Sanitization: No explicit sanitization or filtering of extracted content is documented before interpolation. This behavior is intrinsic to the skill's purpose and is considered safe.
- [SAFE]: All external repository references point to the author's official GitHub repository (
AsiaOstrich/universal-dev-standards), which is consistent with the skill's intended functionality.
Audit Metadata