Skills/Glama/kopitehnik-print-mcp

kopitehnik-print-mcp@r1

CAUTION

Publisher claims: "Enables MCP clients to drive a Windows print workstation by opening photo folders, setting formats, cropping and color-correcting images, planning sheets, running preflight checks, and printing photos or documents under configurable permission limits." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry GlamaPublisher ildargiv · joined 1 days agoInstalls 0Last detonated 1 h ago
What would fix thisWatchDispute verdict

Is kopitehnik-print-mcp@r1 safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-11-06 and scored it 71/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Outbound HTTP to raw IP address; Latin word with Cyrillic or Greek look-alike letters (homoglyph); Latin word with Cyrillic or Greek look-alike letters (homoglyph). Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

HIGH
Outbound HTTP to raw IP addressagent_bridge.py:151 · 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
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:44 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detecteddoc_tools.py:115 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:28 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectednet_link.py:154 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:16 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:12 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
README directs the reader to a committed installerREADME.md:66Fix: Pin versions and sources; vendor anything fetched at install time.
AST06
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:32 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
URL using raw IP addressagent_bridge.py:151 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:40 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:24 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Latin word with Cyrillic or Greek look-alike letters (homoglyph)epson_dlg_tree.txt:20 · Latin word with Cyrillic or Greek look-alike letters (homoglyph)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
MEDIUM
Python subprocess execution detectedoffice_convert.py:279 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.tr.md:31 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionRELEASE_NOTES.id.md:11 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedupdater.py:187 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionREADME.id.md:5 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedoffice_convert.py:295 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
LOW
Prompt injectionRELEASE_NOTES.id.md:12 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionRELEASE_NOTES.id.md:7 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.id.md:27 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionRELEASE_NOTES.id.md:8 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Prompt injectionREADME.id.md:25 · Prompt injection — known jailbreak technique reference · informational: not an instruction fileFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Unicode escape sequence detectednet_link.py:72 · Unicode escape sequence detected — may contain obfuscated payloadsFix: 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 detectedphoto_crop.py:2590 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05

Cost to the agent

Instructions loaded
≈40 tok
1 file · 81 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.

What would make this Verified

9 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. README directs the reader to a committed installer≈ +9 on the totalPin versions and sources; vendor anything fetched at install time.
  2. Unclaimed publisher≈ +8 on the totalClaim ildargiv: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Outbound HTTP to raw IP address≈ +4 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
  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. Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
  6. URL using raw IP address≈ +2 on the totalReplace encoded or assembled strings with plain literals and remove undeclared network calls.
Publish a new version to Glama, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim ildargivPropose a patch to the maintainer