Back to skill

Security audit

Agent Matchmaking

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent agent-matchmaking skill with a normal dependency-install caveat, and the scanner credential warning is not supported by the artifact text.

Install this in a virtual environment and consider pinning `agent-matchmaking` to a reviewed version before use. Be aware that profile publishing, federation, or agent search may share capability and pricing metadata with external registries depending on the package behavior.

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
SKILL.md:27
Finding
Unpinned Third-Party Package Installation## Vulnerability Details **File Location**: `SKILL.md`, lines 27–31 **Vulnerability Type**: Unpinned third-party dependency installation **Risk Level**: Medium ```markdown ## Setup ```bash pip install agent-matchmaking ``` ``` ### Technical Analysis The setup instructions install the `agent-matchmaking` package from PyPI without pinning an exact version or verifying package hashes. Consequently, the code installed by this command can change after the skill has been reviewed. The package implementation and its transitive dependencies are not included in the audited project, so their behavior cannot be verified from `SKILL.md`. An unpinned package installation exposes users to software supply-chain risks, including a compromised publisher account, a malicious future release, or compromise of a transitive dependency. Python packages may execute code during installation or when imported by the examples later in the document. ### Attack Path 1. An attacker compromises the package publisher, package repository account, release process, or a transitive dependency. 2. The attacker publishes a malicious version under the package name expected by the skill. 3. A user follows the documented setup instruction and runs `pip install agent-matchmaking`. 4. Pip resolves and downloads the attacker-controlled release because no trusted version or hash is specified. 5. Malicious code executes during installation or when the package is imported and used. ### Impact Assessment Malicious package code could execute with the privileges of the user running `pip` or the Python examples. Depending on those privileges and the runtime environment, this could permit access to readable files, credentials, environment variables, network resources, and writable project or user files. The code could also alter local state or install additional payloads. The exact impact cannot be established because the external package was not present in the audi ...[truncated 13 chars]
Remediation
## Remediation Suggestions - Pin the dependency to a specific version that has undergone security review, for example `agent-matchmaking==X.Y.Z`. - Record cryptographic hashes in a lock file or requirements file and install with pip's `--require-hashes` option. - Lock and review all transitive dependencies rather than only the top-level package. - Document the authoritative source repository and verify release provenance or signatures where available. - Perform a separate source-code and dependency audit of the pinned package before recommending installation. - Prefer an isolated virtual environment with minimal filesystem, network, and credential access. - Use automated dependency and provenance monitoring to detect compromised or vulnerable releases.
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Credential Access

High
Category
Privilege Escalation
Content
**What it cannot do:**
- Cannot access files outside your working directory beyond what you explicitly specify
- Cannot make purchases, send emails, or take irreversible actions
- Cannot access credentials, environment variables, or secrets

**License:** Apache 2.0
Confidence
70% confidence
Finding
Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Static analysis

No suspicious patterns detected.