scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
mkdir,git mv,git commit, andpnpm ai-hero-clito scaffold and validate directory structures.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes user-supplied plans to generate directory names used in shell commands. If the plan contains malicious characters, it could lead to command injection.\n - Ingestion points: User-provided plan text in
SKILL.md.\n - Boundary markers: None present; the agent is not instructed to isolate user data or ignore instructions within the plan.\n
- Capability inventory: Access to shell for file creation, git operations, and local package execution.\n
- Sanitization: No sanitization or validation steps are defined for the extracted names before they are interpolated into shell commands.
Audit Metadata