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 executes local shell and PowerShell scripts located in the project's
.specify/extensions/git/scripts/directory. These scripts are invoked with arguments derived from user input. - Evidence:
.specify/extensions/git/scripts/bash/create-new-feature.sh --json --short-name "<short-name>" "<feature description>"and similar PowerShell variants. - [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input (feature descriptions and branch names) and interpolates them directly into shell commands without explicit instructions for sanitization or escaping.
- Ingestion points: User-provided
$ARGUMENTSand<feature description>. - Boundary markers: None present to delineate user input from command parameters.
- Capability inventory: Subprocess execution of Bash and PowerShell scripts.
- Sanitization: No explicit escaping or validation logic is defined in the skill to handle potentially malicious characters in the user-supplied strings.
Audit Metadata