scaffold-exercises
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands including
mkdir -pto create directories,git mvandgit commitfor version control, andpnpm ai-hero-cli internal lintto validate the created structures. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to parse a user-provided plan to determine the folder structure, which represents an attack surface for indirect instructions. Ingestion points: The user-supplied 'plan' described in Workflow step 1 (SKILL.md). Boundary markers: None identified. Capability inventory: File system creation via
mkdir, Git operations, and execution of thepnpmcommand (SKILL.md). Sanitization: No explicit sanitization of the input plan is described.
Audit Metadata