Skills/PyPI/emotional-deescalation-mcp

emotional-deescalation-mcp@0.4.4

VERIFIED

Publisher claims: "MCP server for emotional analysis, de-escalation, and strategic dialogue management in customer support" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher ilyajob05 · joined 4 days agoInstalls 58Last detonated 4d ago
$claude mcp add emotional-deescalation-mcp -- uvx emotional-deescalation-mcp
WatchReport an issue

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-30 and scored it 87/100 (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 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.1sprocessdependency install exit 1
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/emotional-deescalation-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/emotional-deescalation-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only

Static findings

CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt_en.md:145 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt.md:141 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt.md:142 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt_en.md:139 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedsrc/nlp/spacy_singleton.py:71 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt_en.md:146 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt.md:147 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt_en.md:140 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt.md:148 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt_en.md:183 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptprompts/support_bot_system_prompt.md:185 · Prompt injection attempt — model control tokensFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01