agent-docs-api-openapi
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill defines shell-based hooks in its metadata to automate file discovery.
- Evidence:
find . -name "*.route.js" -o -name "*.controller.js" -o -name "routes.js" | grep -v node_modules | head -10inpre_executionhook. - Evidence:
find . -name "openapi.yaml" -o -name "swagger.yaml" -o -name "api.yaml" | grep -v node_modulesinpre_executionhook. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to read and process untrusted project files (source code and existing API specs) to generate documentation.
- Vector: Ingests content from
.js,.yaml, and.mdfiles within the workspace. - Capability: The skill has
WriteandEditpermissions, allowing it to modify the filesystem based on the processed (potentially malicious) input.
Audit Metadata