hyperlight-codeact — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited hyperlight-codeact (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Collapse multi-step tool chains into a single sandboxed Python execution inside an isolated Hyperlight micro-VM (WebAssembly).
Use call_tool(name, **kwargs) — built-in global, no import needed:
content = call_tool('view', path='src/main.py')
files = call_tool('glob', pattern='**/*.py')
hits = call_tool('grep', pattern='TODO', paths='src')
result = call_tool('bash', command='git log --oneline -5')
call_tool('edit', path='config.json', old_str='"debug": false', new_str='"debug": true')call_tool('glob', ...) → list of strings like ["src/app.py", ...]call_tool('view', ...) → string (file content)call_tool('bash', ...) → dict with stdout, stderr, returncodecall_tool('mcp_call', ...) → stringfor f in call_tool('glob', pattern='src/**/*.py'):
try:
content = call_tool('view', path=f)
except Exception:
continue
# analyze content...
print(f"{f}: {result}")glob() returns workspace-relative paths — pass directly to view().call_tool('glob', pattern='src/{db,services}/**/*.py')python3 scripts/codeact.py --discover # JSON manifest
python3 scripts/codeact.py --instructions # LLM-ready referenceTools are auto-detected based on what's installed on the host.
uv run --python 3.13 --with 'hyperlight-sandbox[wasm,python_guest]>=0.3.0' \
python3 scripts/codeact.py --auto --workspace . --code '...'Output: {"stdout": "...", "stderr": "...", "exit_code": 0, "success": true}
Sandboxed code can only reach the outside world through call_tool() bridges. Tools run on the host with full process access. Use --workspace to restrict file tools to a directory tree.
uv (recommended) or pip install 'hyperlight-sandbox[wasm,python_guest]>=0.3.0'~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.