iflow-mcp-muhammadindar-mcp-rlm@0.1.0
VERIFIEDPublisher claims: "MCP-RLM: Recursive Language Model Agent for infinite context processing" Observed in sandbox: no network, touches nothing outside the project, writes no memory.
$claude mcp add iflow-mcp-muhammadindar-mcp-rlm -- uvx iflow-mcp_muhammadindar-mcp-rlm
WatchReport an issueIs [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-03 and scored it 86/100 (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 · 1 s · 2 scenarios · 0 deviationst+CategoryObserved action
0.0sprocessno install scripts in bundle
0.9sprocessdependency install exit 1
1.0sprocessexec /usr/bin/timeout
1.0sprocessexec .venv/bin/mcp-rlm
1.0sprocessexited 127: timeout: failed to run command '.venv/bin/mcp-rlm': No such file or directory
1.0sclaimedno tools/list reply (exit 127)
1.1sprocessscript backend runs setup only
Static findings
CRITICAL
System prompt continuationREADME.md:257 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01HIGH
Access to sensitive file pathsrlm_engine.py:10 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05CRITICAL
System prompt continuationconfig.yaml:45 · System prompt continuation — attempts to append to system instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01