skills/juliusbrussee/cavekit/build/Gen Agent Trust Hub

build

Pass

Audited by Gen Agent Trust Hub on Apr 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill identifies and executes arbitrary shell commands for verification, such as build, test, and lint, which are derived from the project context.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection via the SPEC.md file. It parses this file to determine implementation steps and verification commands without sanitization.
  • Ingestion points: The skill reads SPEC.md and FORMAT.md at the start of the process.
  • Boundary markers: There are no explicit delimiters or instructions to ignore embedded commands within the processed files.
  • Capability inventory: The skill possesses the ability to write to the file system (edit code) and execute shell commands (verification).
  • Sanitization: No validation or escaping of the content read from the specification files is performed before it influences the agent's actions.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 20, 2026, 01:09 PM