Back to skill

Security audit

arkcli-agent

Security checks for vulnerabilities and agentic risk

Overview

The skill is marked suspicious because scanners report guidance to create cloud environments with unrestricted networking, while the review was incomplete.

Consider avoiding installation until the unrestricted-networking guidance is clarified or corrected. The scan covered 11 of 12 components, with one partially inspected and unresolved references, so the evidence is incomplete; the suspicious verdict signals review-worthy risk, not a claim that the author acted maliciously.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Rogue AgentSelf-Modification, Session Persistence
Findings (13)

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/interfaces-gaps.md (reported line 10)May include surrounding context.

md
- Env: `CreateEnvironment` / `GetEnvironment` / `ListEnvironments` / `UpdateEnvironment` / `DeleteEnvironment`
- Session: `CreateSession` / `GetSession` / `ListSessions` / `UpdateSession` / `DeleteSession`
- Session data-plane: `GET/POST /api/v3/sessions/:session_id/resources`, `GET/POST /api/v3/sessions/:session_id/events`, `GET /api/v3/sessions/:session_id/events/stream`, `GET /api/v3/sessions/:session_id/threads`, `GET /api/v3/sessions/:session_id/threads/:thread_id`
- Files data-plane: `GET/POST /api/v3/files`, `GET/DELETE /api/v3/files/:file_id`
- Memory: `ListMemoryStores` / `CreateMemoryStore` / `ListMemories` / `CreateMemory` 等
- Vault: `ListVaults` / `CreateVault` / `ListOAuthProviders` / `CreateVaultOAuthFlow` / `ListCredentials` / `CreateCredential` 等

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/mcp-vault.md (reported line 40)May include surrounding context.

md
--mcp-server-url https://example.com/mcp \
  --access-token @./access-token.txt \
  --client-id <client-id> \
  --client-secret @./client-secret.txt \
  --refresh-token @./refresh-token.txt \
  --token-endpoint https://example.com/oauth/token \
  --scope read \

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · references/mcp-vault.md (reported line 47)May include surrounding context.

--format json

text

这会写入 `Auth.Refresh`,其中 client secret 位于 `TokenEndpointAuth.ClientSecret`,由后端负责托管换签。也可以继续使用 `--auth @./credential.json` 透传完整对象;快捷参数会覆盖对象中同名字段。

## OAuth MCP 登录

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · references/skills.md (reported line 74)May include surrounding context.

md
arkcli agent skill github import owner/repo --all --format json
arkcli agent agent create --name arkcli-local-skill-agent --model <items[].model from agent model list> --skill-zip ./my-skill.zip --format json
arkcli agent agent create --name arkcli-existing-custom-skill-agent --model <items[].model from agent model list> --skill skill-xxx --format json
arkcli agent skill update skill-xxx --zip ./my-skill-v2.zip --format json
arkcli --page-all agent skill versions skill-xxx --format json
# 将占位符替换为上一条 versions 响应中选定条目的 Version 原值;不要自行拼版本号:
arkcli agent skill download skill-xxx --version '<Version-from-versions>' --output ./skill-selected-version.zip --format json

The validation workflow creates a cloud environment with unrestricted networking without warning about the security implications.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The validation template creates an agent environment with unrestricted networking without explaining the exposure or establishing that the test needs it. If the agent executes malicious or compromised content, unrestricted connectivity can facilitate data exfiltration or communication with attacker-controlled services; actual impact depends on the environment's accessible data and credentials.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/mcp-vault.md (reported line 72)May include surrounding context.

arkcli agent +mcp-login
--vault-id vlt-xxx
--name arkcli-github-mcp-oauth-
--mcp-server-url https://api.githubcopilot.com/mcp/
--format json

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/mcp-vault.md (reported line 99)May include surrounding context.

arkcli agent agent create
--name arkcli-mcp-agent
--model <items[].model from agent model list>
--mcp-server '{type: url, name: github, url: https://api.githubcopilot.com/mcp/}'
--tool @tools-with-default-agent-toolset-and-github-mcp.json

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/mcp-vault.md (reported line 110)May include surrounding context.

bash
arkcli agent vault oauth-provider list --limit 100 --format json
arkcli agent vault create --display-name arkcli-mcp-login-vault-20260706 --format json
arkcli agent +mcp-login --vault-id vlt-xxx --name arkcli-github-mcp-oauth-20260706 --mcp-server-url https://api.githubcopilot.com/mcp/ --format json

Cloud environment creation requires unrestricted networking without explaining the security implications.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The source recommends unrestricted networking and presents it as required, while the stated validation error only establishes that a networking configuration must be supplied. This can unnecessarily remove a containment boundary for agent workloads, enabling malicious tasks or compromised setup scripts to communicate with arbitrary destinations.

Content

No source excerpt is available for this finding.