Is reforge-mcp@0.3.2 safe to install?

reforge-mcp@0.3.2

CAUTION

Publisher claims: "MCP server that automatically cleans up messy vibe-coded repositories" Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher codewithaiyan · joined 2 days agoInstalls 12Last detonated 2d ago

What would fix this Watch Dispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-11-01 and scored it 68/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Destructive command against a filesystem root or device; Destructive command against a filesystem root or device; Prompt injection. 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

0.2sprocessdependency install exit 1

0.2sprocessexec /usr/bin/timeout

0.2sprocessexec .venv/bin/reforge-mcp

0.2sprocessexited 127: timeout: failed to run command '.venv/bin/reforge-mcp': No such file or directory

0.2sclaimedno tools/list reply (exit 127)

0.2sprocessscript backend runs setup only

Static findings

CRITICAL

Destructive command against a filesystem root or devicesrc/reforge_mcp/utils/security.py:260 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

CRITICAL

Destructive command against a filesystem root or devicesrc/reforge_mcp/utils/security.py:222 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

CRITICAL

Prompt injectionIMPROVEMENTS.md:516 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

CRITICAL

Destructive command against a filesystem root or devicesrc/reforge_mcp/utils/security.py:261 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

CRITICAL

Prompt injectionIMPROVEMENTS.md:511 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.

AST01

MEDIUM

Destructive file system command detectedtests/test_fix.py:97 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Authorization escalation languageIMPROVEMENTS.md:511 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

HIGH

Destructive file system command detectedsrc/reforge_mcp/utils/security.py:222 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Access to sensitive file pathssrc/reforge_mcp/utils/security.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.

AST05

MEDIUM

Destructive command against a filesystem root or devicetests/test_security.py:343 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Destructive file system command detectedtests/test_security.py:232 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Destructive file system command detectedsrc/reforge_mcp/utils/security.py:261 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedtests/test_kotlin_graph.py:33 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Access to sensitive file pathstests/test_git.py:83 · 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

Destructive command against a filesystem root or devicetests/test_security.py:232 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Access to sensitive file pathssrc/reforge_mcp/utils/security.py:35 · 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

File type combined with upload action.claude/settings.json:9 · 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.

AST07

MEDIUM

Python subprocess execution detectedsrc/reforge_mcp/tools/fix.py:116 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Destructive command against a filesystem root or devicetests/test_fix.py:97 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Access to sensitive file pathssrc/reforge_mcp/utils/security.py:64 · 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

Python subprocess execution detectedtests/test_kotlin_graph.py:32 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

HIGH

Destructive file system command detectedsrc/reforge_mcp/utils/security.py:260 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Destructive command against a filesystem root or devicetests/test_security.py:245 · Destructive command against a filesystem root or deviceFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

HIGH

Authorization escalation languageIMPROVEMENTS.md:516 · Authorization escalation languageFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.

AST01

HIGH

Access to sensitive file pathssrc/reforge_mcp/utils/security.py:65 · 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

Python subprocess execution detectedtests/test_kotlin_graph.py:31 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Access to sensitive file pathstests/test_security.py:282 · 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

Destructive file system command detectedtests/test_security.py:245 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Access to sensitive file pathstests/test_security.py:258 · 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

Access to sensitive file pathstests/test_security.py:130 · 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

Access to sensitive file pathstests/test_security.py:128 · 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

Python subprocess execution detectedtests/test_sweep_findings.py:24 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

MEDIUM

Destructive file system command detectedtests/test_security.py:343 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.

AST05

MEDIUM

Python subprocess execution detectedtests/test_sweep_findings.py:25 · 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_sweep_findings.py:23 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.

AST05

What would make this Verified

12 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%

Destructive command against a filesystem root or device≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Unclaimed publisher≈ +8 on the totalClaim codewithaiyan: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
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.
Destructive file system command detected≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
Python subprocess execution detected≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.

Publish a new version to PyPI, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim codewithaiyan