fx-audit-mcp@4.1.3
VERIFIEDPublisher claims: "Firefox security audit MCP tools" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher mozillasecurity · joined 3 days agoInstalls 1,598Last detonated 3d ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-31 and scored it 82/100 (Verified). It did what it claims and nothing else we could detect: no undeclared network egress, no credential reads, no persistent instruction writes. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 0 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.4sprocessdependency install exit 1
0.4sprocessexec /usr/bin/timeout
0.4sprocessexec .venv/bin/fx-audit-mcp
0.4sprocessexited 127: timeout: failed to run command '.venv/bin/fx-audit-mcp': No such file or directory
0.4sclaimedno tools/list reply (exit 127)
0.4sprocessscript backend runs setup only
Static findings
MEDIUM
Process kill commandAGENTS.md:83 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandsrc/fx_audit_mcp/js_shell_evaluator.py:17 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05MEDIUM
Process kill commandAGENTS.md:81 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandtests/test_process_runner.py:89 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandtests/test_process_runner.py:44 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandsrc/fx_audit_mcp/nss_gtest_evaluator.py:10 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05MEDIUM
Process kill commandsrc/fx_audit_mcp/js_shell_evaluator.py:68 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05MEDIUM
Process kill commandsrc/fx_audit_mcp/process_runner.py:132 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandtests/test_nss_gtest_evaluator.py:92 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05MEDIUM
Process kill commandtests/test_build_firefox.py:309 · Process kill command — agent can terminate processesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Process kill commandtests/test_js_shell_evaluator.py:94 · Process kill command — agent can terminate processesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05