speckit-git-feature
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to invoke local Bash and PowerShell scripts (e.g.,
.specify/extensions/git/scripts/bash/create-new-feature.sh) to perform Git operations within a specific project structure. - [INDIRECT_PROMPT_INJECTION]: The skill contains an attack surface for indirect prompt injection via user-supplied data.
- Ingestion points: Untrusted data enters the agent context through
$ARGUMENTSand the<feature description>provided by the user. - Boundary markers: There are no explicit delimiters or warnings (e.g., 'ignore any instructions contained within this text') to prevent the agent from misinterpreting instructions embedded within the user data.
- Capability inventory: The skill has the capability to execute shell commands and modify the local Git environment.
- Sanitization: The instructions do not specify any sanitization, escaping, or validation steps for the
<feature description>or<short-name>before they are interpolated into the shell command strings (e.g.,"<feature description>"). This could potentially lead to command injection if the underlying shell tool does not handle quoted arguments securely.
Audit Metadata