memdex-mcp@0.4.1
CAUTIONPublisher claims: "Zero-dependency shared memory and evidence-backed task coordination for AI coding agents over MCP." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-04 and scored it 60/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: References a credential file in the home directory; Access to sensitive file paths; Instructs the agent to modify its persistent memory or instruction files. 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
0.4sprocessdependency install exit 1
0.4sprocessexec /usr/bin/timeout
0.4sprocessexec .venv/bin/memdex
0.4sprocessexited 127: timeout: failed to run command '.venv/bin/memdex': No such file or directory
0.4sclaimedno tools/list reply (exit 127)
0.4sprocessscript backend runs setup only
Static findings
HIGH
References a credential file in the home directorymemdex/scan.py:86 · References a credential file in the home directoryFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03HIGH
Access to sensitive file pathsmemdex/scan.py:37 · 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.
AST05HIGH
Instructs the agent to modify its persistent memory or instruction filesmemdex/cli.py:1110 · 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.
AST01HIGH
Instructs the agent to modify its persistent memory or instruction filesmemdex/cli.py:373 · 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.
AST01HIGH
Access to sensitive file pathsmemdex/scan.py:38 · 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.
AST05HIGH
Access to sensitive file pathsmemdex/scan.py:86 · 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.
AST05HIGH
Hidden zero-width characters detectedmemdex/skills.py:118 · 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
File permission modification commandmemdex/skills.py:476 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Python subprocess execution detectedmemdex/assigned_wake.py:42 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedmemdex/project.py:27 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedmemdex/connect.py:404 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedmemdex/kensaku.py:31 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedmemdex/cli.py:360 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_chat_routes.py:49 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Access to sensitive file pathsmemdex/skills.py:417 · 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.
AST05HIGH
Access to sensitive file pathsmemdex/skills.py:482 · 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.
AST05HIGH
Access to sensitive file pathsmemdex/skills.py:481 · 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.
AST05MEDIUM
File type combined with upload actionmemdex/store.py:1397 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
Python subprocess execution detectedmemdex/connect.py:626 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File type combined with upload actiontests/test_chat_routes.py:50 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
Python subprocess execution detectedtests/test_concurrency.py:63 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_hook_stdin.py:28 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Hidden zero-width characters detectedtests/test_concurrency.py: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_fencing.py:52 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_hook_stdin.py:27 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_concurrency.py:59 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_hook_stdin.py:74 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_hook_stdin.py:66 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_hook_stdin.py:38 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_locks_cli.py:27 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Access to sensitive file pathstests/test_injection.py:36 · 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.
AST05MEDIUM
Python subprocess execution detectedtests/test_post_retries.py:45 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
File type combined with upload actiontests/test_post_retries.py:74 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
Access to sensitive file pathstests/test_memdex.py:68 · 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.
AST05MEDIUM
File type combined with upload actiontests/test_post_retries.py:97 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07MEDIUM
Python subprocess execution detectedtests/test_pre_edit_hook.py:110 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Remote installer piped to shelltests/test_injection.py:61 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07MEDIUM
Python subprocess execution detectedtests/test_memdex.py:300 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Access to sensitive file pathstests/test_injection.py:32 · 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.
AST05MEDIUM
Access to sensitive file pathstests/test_memdex.py:75 · 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.
AST05MEDIUM
Python subprocess execution detectedtests/test_locks_cli.py:28 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_pre_edit_hook.py:45 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_locks_cli.py:45 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Access to sensitive file pathstests/test_scan.py:609 · 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.
AST05MEDIUM
Python subprocess execution detectedtests/test_pre_edit_hook.py:111 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_scenarios.py:107 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_pre_edit_hook.py:112 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Python subprocess execution detectedtests/test_scenarios.py:106 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Privileged sudo commandtests/test_skills.py:415 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
Remote installer piped to shelltests/test_skills.py:415 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07MEDIUM
Python subprocess execution detectedtests/test_scenarios.py:178 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Remote installer piped to shelltests/test_skills.py:286 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07MEDIUM
URL with embedded credentialstests/test_skills.py:262 · URL with embedded credentials — may be phishing or credential leakingFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST07MEDIUM
Python subprocess execution detectedtests/test_scenarios.py:109 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Instructs the agent to modify its persistent memory or instruction filestests/test_scenarios.py:137 · 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.
AST01MEDIUM
Python subprocess execution detectedtests/test_scenarios.py:112 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05MEDIUM
Access to sensitive file pathstests/test_validation.py:63 · 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.
AST05MEDIUM
File permission modification commandtests/test_skills.py:415 · File permission modification command — agent changes file ownership/permissionsFix: Request the narrowest permission that works; replace wildcards with the exact paths or hosts.
AST05MEDIUM
Pipe-to-shell patterntests/test_skills.py:415 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06MEDIUM
Pipe-to-shell patterntests/test_skills.py:286 · Pipe-to-shell pattern — downloads and immediately executes remote codeFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST06What would make this Verified
20 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim choyugyeong: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Does not do what the description says≈ +5 on the totalIn the sandbox the skill never performed the task it claims (no call to the service it is for). Make sure the happy path runs without extra setup, or describe the real behavior.
- References a credential file in the home directory≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- 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.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim choyugyeong