scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Jul 11, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands such as
mkdir -p,git mv, andgit committo manage the exercise file system structure. - [COMMAND_EXECUTION]: It invokes a local command
pnpm ai-hero-cli internal lintto perform automated validation of the created stubs. - [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where user-provided exercise plans are used to construct directory paths and file content. Evidence Chain: (1) Ingestion points: Plan parsing in Workflow step 1; (2) Boundary markers: Absent; (3) Capability inventory: Subprocess calls (
mkdir,pnpm) and file writes in SKILL.md; (4) Sanitization: Absent. This surface is considered low-risk given the skill's intended development purpose.
Audit Metadata