Back to skill

Security audit

CISO Agent Security

Security checks for vulnerabilities and agentic risk

Overview

The skill is a coherent security-assessment guide, but it tells agents to quarantine failing agents immediately without clear approval, scope, or rollback controls.

Review this before installing in an autonomous environment. Treat the quarantine instruction as requiring explicit human approval and define what quarantine means, who can trigger it, how to reverse it, and what agents or systems it may affect. Prefer the ClawHub or manual install path over the unpinned npx command unless you have verified the package source and version.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
README.md:46
Finding
Unpinned Package Execution Through npx## Vulnerability Details **File Location**: `README.md:46-50` **Vulnerability Type**: Supply-chain risk from an unpinned executable dependency **Risk Level**: Medium ```markdown ### skills.sh ```bash npx skills add Crevita/ciso-agent-security ``` ``` ### Technical Analysis The installation instructions invoke the `skills` package through `npx` without specifying an exact package version or verifying its integrity. Depending on the local environment and cache state, `npx` can retrieve the current package release from the configured npm registry and execute it. Consequently, the code executed by this command is not immutable relative to the audited repository. A compromised registry account, malicious future package release, registry substitution, or unsafe registry configuration could cause users to execute code that was never reviewed as part of this skill. The repository itself contains no malicious script or executable payload. The risk arises specifically from recommending execution of an unpinned third-party package. ### Attack Path 1. An attacker compromises the npm package, its publisher account, or an upstream dependency used by the `skills` package. 2. The attacker publishes a malicious release under the package name resolved by `npx`. 3. A user follows the documented installation command. 4. `npx` resolves and downloads the attacker-controlled release from the configured registry. 5. Package lifecycle logic or the invoked CLI executes with the installing user's permissions. 6. The malicious code can access resources available to that user and potentially alter the project or local environment. ### Impact Assessment Successful exploitation could provide arbitrary code execution with the privileges of the user running the installation command. The reachable scope may include the current project, user-owned files, environment variables, accessible credentials or tokens, and network resources available to that account. No privilege escalation be ...[truncated 184 chars]
Remediation
## Remediation Suggestions - Pin the installer to an explicitly reviewed package version rather than allowing `npx` to resolve the latest release. - Use an organization-controlled lockfile and verify package integrity with the expected registry checksum. - Document the trusted registry, exact publisher identity, approved version, and expected integrity digest. - Review the package's lifecycle scripts and transitive dependencies before recommending execution. - Prefer a non-executing installation method, such as downloading and verifying the skill file before manually copying it into place. - In automated environments, install dependencies using reproducible, lockfile-enforcing commands and disable lifecycle scripts unless they are explicitly required and audited. - Run installation under a least-privileged account without production credentials or unnecessary filesystem access.
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding
The README instructs users to run `npx skills add Crevita/ciso-agent-security` without pinning a package version or commit, which can cause execution of whatever package is currently resolved from the registry at install time. If the package is replaced, compromised, typo-squatted, or a dependency is poisoned, users may execute attacker-controlled code during installation.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill instructs the agent to 'Quarantine agent immediately' for scores below 60, but it does not define any required human approval, confirmation flow, rollback plan, or impact disclosure before taking that potentially disruptive action. In a security automation skill for autonomous agents, this creates a real risk of unsafe or attacker-induced denial of service if scoring is manipulated or produces false positives.

Static analysis

Detected: suspicious.prompt_injection_instructions

Prompt-injection style instruction pattern detected.

Warn
Code
suspicious.prompt_injection_instructions
Location
README.md:40