rightcode-scaffold-exercises

Pass

Audited by Gen Agent Trust Hub on May 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes shell commands including mkdir, git mv, git commit, and pnpm to create directories and manage files within the workspace. These operations are essential to its documented purpose.
  • [PROMPT_INJECTION]: The workflow involves parsing a user-provided "plan" to determine the names and types of directories to be created. This introduces an indirect prompt injection surface where a maliciously crafted plan could attempt to execute command injection or influence agent behavior.
  • Ingestion points: The skill parses a "plan" in the first step of the workflow described in SKILL.md.
  • Boundary markers: There are no explicit delimiters or instructions provided to isolate or ignore malicious content within the plan.
  • Capability inventory: The skill uses mkdir, git, and pnpm for file system and project management as defined in SKILL.md.
  • Sanitization: No input validation or sanitization procedures are specified for the names or content derived from the plan before they are used in shell commands.
Audit Metadata
Risk Level
SAFE
Analyzed
May 13, 2026, 04:43 AM
Security Audit — agent-trust-hub — rightcode-scaffold-exercises