Skills/PyPI/evermemos-mcp

evermemos-mcp@0.5.7

CAUTION

Publisher claims: "MCP Server that brings long-term memory to AI coding tools via EverMemOS" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher tt-a1i · joined 12 days agoInstalls 128Last detonated 3d ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-31 and scored it 64/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Instructs the agent to modify its persistent memory or instruction files; Prompt injection; Access to sensitive file paths. 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/evermemos-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/evermemos-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only

Static findings

MEDIUM
Outbound HTTP to raw IP addresstests/test_evermemos_client.py:139 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
GitHub token pattern detectedtests/test_content_guard.py:134 · GitHub token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
HIGH
Instructs the agent to modify its persistent memory or instruction filesdocs/auto-memory-prompt.md:9 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
GitHub token pattern detectedtests/test_content_guard.py:34 · GitHub token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
CRITICAL
Prompt injectionCHANGELOG.md:26 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedtests/test_competition_eval_script.py:79 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionscripts/competition_eval.py:5 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Python subprocess execution detectedtests/test_competition_eval_script.py:163 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Slack token pattern detectedtests/test_content_guard.py:91 · Slack token pattern detected — possible hardcoded or harvested tokenFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03
MEDIUM
Python subprocess execution detectedsrc/evermemos_mcp/config.py:138 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
Python subprocess execution detectedtests/test_competition_eval_script.py:135 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Access to sensitive file pathssrc/evermemos_mcp/config.py:15 · 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.
AST05
MEDIUM
URL using raw IP addresstests/test_evermemos_client.py:139 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
AWS access key pattern detectedtests/test_content_guard.py:27 · AWS access key pattern detected — possible hardcoded or harvested keyFix: Never read or enumerate credential locations; accept a documented environment variable instead.
AST03

What would make this Verified

16 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim tt-a1i: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. New publisher≈ +3 on the totalTime clears this on its own after 14 and 30 days. Claiming the handle (+50) is the fastest way past it.
  5. Outbound HTTP to raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  6. GitHub token pattern detected≈ +2 on the totalNever read or enumerate credential locations; accept a documented environment variable instead.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim tt-a1i