Skills/PyPI/finos-mcp-aigf

finos-mcp-aigf@0.3.2

CAUTION

Publisher claims: "Read-only MCP server for the FINOS AI Governance Framework: risks, controls, crosswalks and search. Not affiliated with FINOS." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry PyPI (MCP server)Publisher vardhjain · joined 0 days agoInstalls 899Last detonated 2 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios) on 2026-10-26 and scored it 56/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Rule modification attempt; Prompt injection. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 1 s · 2 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.3sprocessdependency install exit 1
0.4sprocessexec /usr/bin/timeout
0.4sprocessexec .venv/bin/finos-mcp-aigf
0.4sprocessexited 127: timeout: failed to run command '.venv/bin/finos-mcp-aigf': No such file or directory
0.4sclaimedno tools/list reply (exit 127)
0.4sprocessscript backend runs setup only

Static findings

HIGH
Access to sensitive file pathssrc/finos_mcp/aigf/_vendor/mitigations/mi-25_skill-plugin-integrity-and-governance.md:103 · 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
CRITICAL
Rule modification attemptsrc/finos_mcp/aigf/_vendor/references/canada-regulations.yml:155 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionsrc/finos_mcp/aigf/_vendor/risks/ri-10_prompt-injection.md:49 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/finos_mcp/aigf/_vendor/mitigations/mi-25_skill-plugin-integrity-and-governance.md:148 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injection attemptsrc/finos_mcp/aigf/_vendor/mitigations/mi-25_skill-plugin-integrity-and-governance.md:145 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Rule modification attemptsrc/finos_mcp/aigf/_vendor/references/canada-regulations.yml:140 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Prompt injectionsrc/finos_mcp/aigf/_vendor/mitigations/mi-25_skill-plugin-integrity-and-governance.md:145 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Rule modification attemptsrc/finos_mcp/aigf/_vendor/references/canada-regulations.yml:150 · Rule modification attempt — overwriting existing instructionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
CRITICAL
Destructive file system command detectedsrc/finos_mcp/aigf/_vendor/mitigations/mi-18_agent-authority-least-privilege-framework.md:167 · Destructive file system command detectedFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.
AST05
CRITICAL
Prompt injectionsrc/finos_mcp/aigf/_vendor/risks/ri-10_prompt-injection.md:70 · Prompt injection — known jailbreak technique referenceFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptsrc/finos_mcp/aigf/_vendor/mitigations/mi-17_ai-firewall-implementation-and-management.md:123 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injectionsrc/finos_mcp/aigf/_vendor/risks/ri-8_tampering-with-the-foundational-model.md:42 · Prompt injection — explicit attempt to bypass safety measuresFix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
CRITICAL
Prompt injection attemptsrc/finos_mcp/aigf/_vendor/risks/ri-10_prompt-injection.md:55 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
HIGH
Access to sensitive file pathssrc/finos_mcp/aigf/_vendor/mitigations/mi-25_skill-plugin-integrity-and-governance.md:146 · 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
HIGH
Access to sensitive file pathssrc/finos_mcp/aigf/_vendor/risks/ri-30_skill-plugin-supply-chain-compromise.md:57 · 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
URL using raw IP addresstests/test_http.py:69 · 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
Outbound HTTP to raw IP addresstests/test_http.py:69 · 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
Python subprocess execution detectedtests/test_http.py:39 · Python subprocess execution detectedFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST05
HIGH
Instructs the agent to modify its persistent memory or instruction filessrc/finos_mcp/aigf/_vendor/risks/ri-30_skill-plugin-supply-chain-compromise.md:61 · Instructs the agent to modify its persistent memory or instruction filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

What would make this Verified

24 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. 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.
  2. Destructive file system command detected≈ +9 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
  3. Unclaimed publisher≈ +8 on the totalClaim vardhjain: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  4. 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.
  5. 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.
  6. Outbound HTTP to raw IP address≈ +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 vardhjain