livelib-mcp@0.2.0
VERIFIEDPublisher claims: "Anonymous read client for the LiveLib trisolaris API" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Registry PyPI (MCP server)Publisher shared-goals-contributors · joined 2 days agoInstalls 0Last detonated 42 h ago
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-01 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
0.3sprocessdependency install exit 1
0.3sprocessexec /usr/bin/timeout
0.3sprocessexec .venv/bin/livelib-mcp
0.3sprocessexited 127: timeout: failed to run command '.venv/bin/livelib-mcp': No such file or directory
0.3sclaimedno tools/list reply (exit 127)
0.3sprocessscript backend runs setup only
Static findings
MEDIUM
Hidden zero-width characters detectedtests/fixtures/shelf_reads_off200.json:1 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07MEDIUM
Hidden zero-width characters detectedtests/fixtures/shelf_reads_off100.json:1 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07MEDIUM
Dense URL-encoded contenttests/test_client.py:279 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07MEDIUM
Dense URL-encoded contenttests/fixtures/search_auzan.json:1 · Dense URL-encoded content — may be obfuscating payloadsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07MEDIUM
Hidden zero-width characters detectedtests/fixtures/shelf_reads.json:1 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07MEDIUM
Hidden zero-width characters detectedtests/fixtures/shelf_reads_off300.json:1 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07MEDIUM
Python subprocess execution detectedtests/test_server.py:468 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05