speckit-baseline
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow involves executing a local script at
.specify/scripts/bash/create-new-feature.sh. The skill instructions explicitly direct the agent on how to use shell escaping (e.g., handling single quotes) to prevent command injection when passing dynamically generated feature names to the shell script.\n- [PROMPT_INJECTION]: The skill analyzes external source code, which constitutes an indirect prompt injection surface. However, the logic is limited to documentation generation, and the skill does not expose sensitive capabilities or network access to the data being processed.\n- [SAFE]: No evidence of data exfiltration, credential harvesting, or remote code execution was found. The skill operations are confined to the local project environment.
Audit Metadata