Skills/Claude Code plugins/mlflow

mlflow@1.0.0

CAUTION

Publisher claims: "Skills for tracing, evaluating, and improving AI agents with MLflow. Supports the full agent improvement loop: instrument → trace → evaluate → iterate → validate." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry Claude Code plugin marketplacePublisher mlflow · joined 0 days agoInstalls 0Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario) on 2026-10-27 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: System prompt continuation; Access to sensitive file paths; Prompt injection. 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

Static findings

MEDIUM
Python subprocess execution detectedagent-evaluation/scripts/create_dataset_template.py:110 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
System prompt continuationagent-evaluation/references/scorers.md:205 · System prompt continuation — attempts to append to system instructionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
HIGH
Access to sensitive file pathsagent-evaluation/SKILL.md: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
File type combined with upload actionagent-evaluation/scripts/analyze_results.py:18 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
CRITICAL
Prompt injectionfix-agent-issue/SKILL.md:182 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
Python subprocess execution detectedagent-evaluation/scripts/create_dataset_template.py:126 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
File type combined with upload actionagent-evaluation/scripts/analyze_results.py:493 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
File permission modification commandagent-evaluation/scripts/run_evaluation_template.py:285 · File permission modification command — agent changes file ownership/permissionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
HIGH
Destructive file system command detectedfix-agent-issue/SKILL.md:186 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
MEDIUM
File permission modification commandagent-evaluation/scripts/create_dataset_template.py:421 · File permission modification command — agent changes file ownership/permissionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedagent-evaluation/scripts/run_evaluation_template.py:37 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
CRITICAL
System prompt continuationagent-evaluation/references/scorers.md:184 · System prompt continuation — attempts to append to system instructionsFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST01
CRITICAL
Prompt injectionfix-agent-issue/SKILL.md:163 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionagent-evaluation/SKILL.md:494 · File type combined with upload action — agent may exfiltrate local data filesFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST07
MEDIUM
Outbound HTTP to raw IP addresstests/infra.py:149 · 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
MEDIUM
Outbound HTTP to raw IP addresstests/infra.py:122 · 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
MEDIUM
Python subprocess execution detectedtests/test_skill.py:76 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionanalyze-mlflow-chat-session/scripts/discover_schema.sh:33 · 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 detectedagent-evaluation/scripts/validate_environment.py:27 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedagent-evaluation/scripts/utils/env_validation.py:111 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
Python subprocess execution detectedagent-evaluation/scripts/setup_mlflow.py:79 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
URL using raw IP addresstests/infra.py:122 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/infra.py:380 · 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/utils.py:33 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
MEDIUM
File type combined with upload actionanalyze-mlflow-chat-session/scripts/discover_schema.sh:37 · 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
Access to sensitive file pathstests/infra.py:175 · 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/infra.py:173 · 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/scripts/setup_tracing_test.py:12 · 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/infra.py:121 · 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/scripts/setup_agent_eval.py:12 · Python subprocess execution detectedFix: Put hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
AST05
MEDIUM
URL using raw IP addresstests/infra.py:149 · URL using raw IP address — may bypass domain-based filteringFix: Replace encoded or assembled strings with plain literals and remove undeclared network calls.
AST07
MEDIUM
Python subprocess execution detectedtests/infra.py:94 · 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%
  1. Unclaimed publisher≈ +8 on the totalClaim mlflow: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  2. 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.
  3. Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  4. Python subprocess execution detected≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  5. File type combined with upload action≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
  6. File permission modification command≈ +2 on the totalPut hosts, commands and strings in plain source. Decoding at runtime looks identical to malware and costs points on its own.
Publish a new version to Claude Code plugins, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim mlflow