100Critical
This skill facilitates arbitrary remote code execution via unverified shell pipes, enables cross-agent privilege escalation, and bypasses sandbox restrictions to exfiltrate sensitive data through undeclared network access.
Skill Info
NameEximAgent/cli/eximagent
Registrygithub
Versioneba38e31bd03
PURLpkg:github/EximAgent/cli@eba38e31bd03?skill=eximagent
Stars2
Source
SHA-2562a89f9dd9435...
SHA-149af7f8221e8...
MD57a830e920e3c...
TLSH1ea3f9a76b68...
ssdeep1536:+4nXRIj...
Size97,719 bytes
Install
This skill has been flagged as potentially malicious. Review the findings below before installing.
GitHub
Skills.shDocs
npx skills add https://github.com/EximAgent/cliAssessments (6)
AI Agent Traps ↗Description Mismatchcriticaldescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill documentation includes instructions for installing the CLI via a shell pipe (`curl ... | sh` or `irm ... | iex`), which is a high-risk pattern for remote code execution. Additionally, the skill context acknowledges critical findings regarding remote code download/execution and cross-agent privilege escalation that are not addressed in the provided content.
85% confidence
Installation instructions: 'curl -fsSL https://cli.eximagent.ai/install | sh' and 'irm https://cli.eximagent.ai/install.ps1 | iex'. Static analysis context: '[critical] MONDOO_AGENT_SKILL_CE_003 — Remote code download and execution detected'.
Implicit instruction to bypass securitymediumoversight evasionAML.T0054LLM01:2025LLM07:2025
The documentation explicitly instructs the agent to use a specific flag to bypass sandbox network restrictions, which could be exploited to exfiltrate data or reach unauthorized endpoints. [ensemble: confirmed by 2/3 passes; severity set to the agreed median (ADR-0067).]
90% confidenceline 147
re-run with it enabled (e.g. `codex --dangerously-bypass-approvals-and-sandbox`)
Remote code download and execution detectedcriticalremote execAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
Remote code download and execution detected
95% confidenceline 15
curl -fsSL https://cli.eximagent.ai/install | sh
A remote resource is downloaded with curl/wget and piped directly into a shell interpreter (optionally via sudo). The downloaded script runs with no integrity check (no checksum/signature), so a compromised server, MITM, or hijacked URL leads to arbitrary code execution. Download to a file, verify it (e.g. sha256sum -c against a pinned digest, or a signature), then execute it.criticalvulnAML.T0050AML.T0053AML.T0072LLM05:2025LLM06:2025
A remote resource is downloaded with curl/wget and piped directly into a shell interpreter (optionally via sudo). The downloaded script runs with no integrity check (no checksum/signature), so a compromised server, MITM, or hijacked URL leads to arbitrary code execution. Download to a file, verify it (e.g. sha256sum -c against a pinned digest, or a signature), then execute it.
95% confidenceline 1
curl -fsSL https://cli.eximagent.ai/install | sh
Over-privileged tool usagemediumdescription mismatchAML.T0011.000LLM06:2025LLM09:2025
The skill claims to be a 'Trade-intelligence CLI' but includes commands like `analytics sql` which allow arbitrary read-only SQL execution, potentially exposing sensitive trade data beyond the intended scope. [ensemble: confirmed by 3/3 passes; severity set to the agreed median (ADR-0067).]
80% confidence
eximagent analytics sql --query_sql "SELECT ..."
Location detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected location in skill content (confidence: 0.91)
91% confidence
U*
Location detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected location in skill content (confidence: 1.00)
100% confidence
G******
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.58)
58% confidence
m****
Organization name detectedmediumpii exposureAML.T0024LLM02:2025
NER model detected organization in skill content (confidence: 0.71)
71% confidence
O***
Supply chain risk in installationmediumsupply chainAML.T0010AML.T0019AML.T0058LLM03:2025
The installation instructions use `curl | sh` and `irm | iex`, which are classic patterns for executing unverified remote code with high privileges.
90% confidenceline 15
curl -fsSL https://cli.eximagent.ai/install | sh
Cross-agent privilege escalation — credential forwarding or admin access grant to agentscriticalagent impersonationAML.T0053AML.T0051.001LLM06:2025
Cross-agent privilege escalation — credential forwarding or admin access grant to agents
95% confidenceline 1451
share token to
Indirect prompt injection via crawlhighindirect prompt injection
The `crawl run` command fetches arbitrary website content and feeds it into the agent's context for processing, which can be exploited to inject malicious instructions into the agent's reasoning loop.
90% confidence
eximagent crawl run --url https://example.com
Missing licenseinfopolicy violation
Skill does not specify a license field. Specifying a license helps users understand usage terms.
100% confidence
Version History (9)
Badge
Markdown
[](https://mondoo.com/ai-agent-security/skills/github/EximAgent/cli/eximagent)HTML
<a href="https://mondoo.com/ai-agent-security/skills/github/EximAgent/cli/eximagent"><img src="https://mondoo.com/ai-agent-security/api/badge/github/EximAgent/cli/eximagent.svg" alt="Mondoo Skill Check" /></a>Image URL
https://mondoo.com/ai-agent-security/api/badge/github/EximAgent/cli/eximagent.svgSecure your AI agents
Skills can read files, run commands, and access credentials. Mondoo helps organizations manage the security risks of AI agent skills across their entire fleet.
- Continuous scanning of skills across all registries
- Policy enforcement before skills reach your agents
- Integration with your existing security workflow