api-patterns
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides a helper script
scripts/api_validator.pydesigned to be executed locally via the command line. The script performs read-only heuristic analysis of project files to identify common API patterns and potential issues. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests and processes user-provided source code and API specifications.
- Ingestion points: Local files matching patterns such as
*api*.ts,routes/*.js, andopenapi.jsonare read from the project path provided by the user. - Boundary markers: The skill does not employ specific delimiters or instruction-ignore markers when processing the content of analyzed files.
- Capability inventory: The skill's capabilities are limited to local file reading and reporting. It does not include tools for network communication, file system modifications, or arbitrary code execution.
- Sanitization: The provided Python script uses regular expressions and structured JSON parsing to evaluate files, which avoids direct execution of the analyzed content.
Audit Metadata