sdd-verify
Pass
Audited by Gen Agent Trust Hub on Mar 28, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill identifies and executes shell commands for testing and building code based on project configuration files such as package.json, pyproject.toml, and Makefile. This capability is necessary for the skill's verification purpose but allows for the execution of code defined within the project repository.
- [PROMPT_INJECTION]: The skill demonstrates a vulnerability to indirect prompt injection. It ingests untrusted data from various sources (specs/, design.md, tasks.md) to build its compliance matrix and report. There are no boundary markers or sanitization steps mentioned for this external data. Capability inventory: The skill has the ability to execute shell commands (test/build) and write files to the project directory. Ingestion points: files provided by the orchestrator and found in the codebase. Sanitization: None observed.
Audit Metadata