scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Aug 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands, including
mkdir -p,git mv, andgit commit, to create and manage the directory hierarchy for educational content. - [COMMAND_EXECUTION]: The skill executes
pnpm ai-hero-cli internal lint, invoking a CLI tool presumably local to the environment or project to validate the scaffolded output. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by parsing a user-provided 'plan' to determine directory names, exercise titles, and variant types.
- Ingestion points: User-supplied 'plan' text (SKILL.md, 'Workflow' section).
- Boundary markers: Absent; there are no specific delimiters or instructions to ignore potential injection markers within the plan.
- Capability inventory: Directory creation (
mkdir), file move (git mv), and command execution (pnpm). - Sanitization: Absent; the instructions do not specify validation or sanitization of input strings before using them in shell commands or file paths.
Audit Metadata