zig-compiler
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill involves reading and processing source code files and compiler output, which constitutes a potential surface for indirect prompt injection if the ingested data contains adversarial instructions.\n
- Ingestion points: Local Zig source files (e.g.,
src/*.zig), C/C++ files (main.c,main.cpp), and the standard output fromzig targetspiped to a Python script.\n - Boundary markers: The instructions do not define specific delimiters or instructions to ignore potential commands embedded within the processed code files.\n
- Capability inventory: The skill uses subprocess calls for
zig,python3,cmake,make,wasm-opt,wasmtime,cat, andgrepacross theSKILL.mdand reference files.\n - Sanitization: There is no explicit sanitization or filtering of content from source files before they are processed by the compiler or other tools.
Audit Metadata