speckit-check
Pass
Audited by Gen Agent Trust Hub on Apr 6, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the
specify checkcommand to audit the local development environment and detect the presence of required tools like Git and various AI agent interfaces.\n- [PROMPT_INJECTION]: The skill processes and interprets output from thespecify checkcommand to provide user recommendations. This creates a surface for indirect prompt injection (Category 8c: Tool output poisoning), where the agent's logic is influenced by data from a local process.\n - Ingestion points: Command output from
specify checkreferenced in the workflow ofSKILL.md.\n - Boundary markers: None present in the instructions.\n
- Capability inventory: Shell command execution via the agent's toolset.\n
- Sanitization: None; the skill relies on the agent to interpret raw string output.
Audit Metadata