zig-code-review

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its handling of untrusted input. 1. Ingestion points: User-provided Zig code snippets, diffs, and file lists entering the context via user prompts (SKILL.md). 2. Boundary markers: Absent; the instructions do not require the agent to use delimiters or ignore instructions embedded in the code. 3. Capability inventory: The agent is instructed to execute zig version and zig fmt shell commands (SKILL.md). 4. Sanitization: Absent; no validation or escaping of user input is performed before processing.
  • [COMMAND_EXECUTION]: The skill workflow (SKILL.md) requires executing local CLI tools like zig version and zig fmt. These operations are limited to standard, non-malicious toolchain functions necessary for the skill's primary purpose of code review.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 12:59 PM
Security Audit — agent-trust-hub — zig-code-review