allmail-mcp@0.2.0
CAUTIONPublisher claims: "All your mailboxes in any AI agent, over MCP. Runs locally; nothing is sent or trashed without your click." 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 2026-10-27 and scored it 54/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Prompt injection; Privileged sudo command; Bidirectional text override characters detected. 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
0.1sprocessdependency install exit 1
0.2sprocessexec /usr/bin/timeout
0.2sprocessexec .venv/bin/allmail-mcp
0.2sprocessexited 127: timeout: failed to run command '.venv/bin/allmail-mcp': No such file or directory
0.2sclaimedno tools/list reply (exit 127)
0.2sprocessscript backend runs setup only
Static findings
CRITICAL
Prompt injectionREADME.tr.md:23 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Privileged sudo commandsrc/mailmcp/secrets_store.py:15 · Privileged sudo command — agent may execute with elevated privilegesFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05MEDIUM
URL using raw IP addresssrc/mailmcp/web.py:570 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Bidirectional text override characters detectedsrc/mailmcp/imap_backend.py:30 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Hidden zero-width characters detectedtests/test_imap_backend.py:226 · 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
Bidirectional text override characters detectedtests/test_compose.py:132 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Hidden zero-width characters detectedtests/test_imap_backend.py:231 · 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
Outbound HTTP to raw IP addresstests/test_web.py:171 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addresstests/test_web.py:171 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Bidirectional text override characters detectedtests/test_clean.py:62 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addresstests/test_web.py:165 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Outbound HTTP to raw IP addresstests/test_web.py:57 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Hidden zero-width characters detectedtests/test_compose.py:132 · 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
URL using raw IP addresssrc/mailmcp/web.py:828 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Python subprocess execution detectedtests/test_server.py:171 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05HIGH
Bidirectional text override characters detectedsrc/mailmcp/clean.py:56 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addresstests/test_web.py:104 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Outbound HTTP to raw IP addresstests/test_web.py:104 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Outbound HTTP to raw IP addresssrc/mailmcp/web.py:830 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
URL using raw IP addresssrc/mailmcp/web.py:830 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Hidden zero-width characters detectedtests/test_clean.py:62 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07CRITICAL
Prompt injection attemptskill/mailmcp/SKILL.md:44 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01MEDIUM
Outbound HTTP to raw IP addresstests/test_web.py:97 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Hidden zero-width characters detectedsrc/mailmcp/imap_backend.py:30 · 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
URL using raw IP addresstests/test_web.py:97 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07CRITICAL
Prompting user to enter sensitive credentialssrc/mailmcp/web.py:108 · Prompting user to enter sensitive credentials — social engineeringFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST03MEDIUM
URL using raw IP addresstests/test_web.py:57 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Outbound HTTP to raw IP addresssrc/mailmcp/web.py:570 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Hidden zero-width characters detectedsrc/mailmcp/clean.py:56 · 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
Outbound HTTP to raw IP addresstests/test_web.py:165 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07MEDIUM
Access to sensitive file pathstests/test_web.py:272 · 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
Outbound HTTP to raw IP addresssrc/mailmcp/web.py:828 · Outbound HTTP to raw IP address — may bypass domain-based monitoringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07What would make this Verified
26 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- 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.
- Prompting user to enter sensitive credentials≈ +9 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Unclaimed publisher≈ +8 on the totalClaim efelazut: 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.
- Privileged sudo command≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Bidirectional text override characters detected≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim efelazut