generate-feature-package
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Node.js script via the Bash tool to perform file system operations. The command structure interpolates user-provided input directly into a shell string:
node "<skill-dir>/scripts/scaffold-feature.mjs" <name>. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection where a malicious user could provide a feature name containing shell metacharacters to attempt command execution.
- Ingestion points: The
<name>argument inSKILL.mdderived from user input. - Boundary markers: None explicitly defined for the argument interpolation in the bash command.
- Capability inventory: Uses the Bash tool to execute shell commands and the underlying script performs file system modifications via
mkdirSyncandwriteFileSync. - Sanitization: The agent is instructed to convert input to kebab-case before execution, and the script itself validates the name against a strict whitelist regex (
/^[a-z][a-z0-9]*(-[a-z0-9]+)*$/) that blocks shell metacharacters and path traversal.
Audit Metadata