anonymize-mcp@0.10.3
CAUTIONPublisher claims: "MCP server wrapping LINDAT NLP tools — production-grade anonymization, multilingual NER (35 languages), UDPipe (961 models), Charles Translator (8 languages), PONK readability, Korektor spellcheck. Non-commercial use only." 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 65/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Hidden zero-width characters detected; Bidirectional text override characters detected; Hidden zero-width 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
0.1sprocessexec /usr/bin/timeout
0.1sprocessexec .venv/bin/anonymize-mcp
0.1sprocessexited 127: timeout: failed to run command '.venv/bin/anonymize-mcp': No such file or directory
0.1sclaimedno tools/list reply (exit 127)
0.1sprocessscript backend runs setup only
Static findings
HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/maskit_normalize.py:45 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Bidirectional text override characters detectedsrc/anonymize_mcp/maskit_normalize.py:60 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/maskit_normalize.py:47 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/maskit_normalize.py:51 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/maskit_normalize.py:46 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Bidirectional text override characters detectedsrc/anonymize_mcp/maskit_normalize.py:59 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Bidirectional text override characters detectedsrc/anonymize_mcp/maskit_normalize.py:56 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07HIGH
Zero-width characters (hidden text)src/anonymize_mcp/validation.py:40 · Zero-width characters (hidden text)Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Bidirectional text override characters detectedsrc/anonymize_mcp/maskit_normalize.py:58 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07CRITICAL
Prompt injectionREADME.md:144 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/validation.py:40 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/maskit_normalize.py:49 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Hidden zero-width characters detectedsrc/anonymize_mcp/validation.py:102 · Hidden zero-width characters detected — may conceal contentFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST07HIGH
Bidirectional text override characters detectedsrc/anonymize_mcp/maskit_normalize.py:57 · Bidirectional text override characters detected — may hide content directionFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07What would make this Verified
15 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim buggy1111: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Hidden instructions≈ +6 on the totalRemove HTML comments, zero-width characters and white-on-white text that carry instructions. Everything the agent is meant to read should be visible to the person reading the file.
- 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.
- Hidden zero-width characters detected≈ +4 on the totalKeep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
- 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 buggy1111