Back to skill

Security audit

OpenAlexandria

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed OpenAlexandria client, but it can send API keys and submitted research bundles to configurable remote endpoints without enough destination or submission safeguards.

Review the destination before use, keep OPENALEXANDRIA_BASE_URL on a trusted HTTPS node, and inspect bundle JSON carefully before submitting. Do not submit prompts, credentials, private files, personal data, or confidential research unless you intend that node to receive and possibly retain it.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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 (3)

T09 · Insecure Skill Coding Practices

Error
Location
openalexandria_cli.py:13
Finding

Bearer credentials and submission data can be transmitted to an arbitrary or insecure endpoint

Content
View full analysis
str: return os.environ.get("OPENALEXANDRIA_BASE_URL", DEFAULT_BASE).rstrip("/") def http_json(method: str, url: str, payload=None, api_key: str | None = None): data = None headers = {"Accept": "application/json"} if api_key: headers["Authorization"] = f"Bearer {api_key}" if payload is not None: raw = json.dumps(payload).encode("utf-8") data = raw headers["Content-Type"] = "application/json; charset=utf-8" req = urllib.request.Request(url, data=data, method=method, headers=headers) try: with urllib.request.urlopen(req, timeout=30) as resp: body = resp.read().decode("utf-8") ``` Affected authenticated operations include: ```python def cmd_whoami(args): api_key = args.api_key or DEFAULT_API_KEY if not api_key: raise SystemExit("Missing API key. Set OPENALEXANDRIA_API_KEY or pass --api-key.") url = base_url() + "/v1/whoami" return http_json("GET", url, api_key=api_key) ``` ```python def cmd_submit(args): if args.file: with open(args.file, "r", encoding="utf-8") as f: payload = json.load(f) else: payload = json.load(sys.stdin) api_key = args.api_key or DEFAULT_API_KEY if not api_key: raise SystemExit("Missing API key. Set OPENALEXANDRIA_API_KEY or pass --api-key.") url = base_url() + "/v1/submit" return http_json("POST", url, payload=payload, api_key=api_key) ``` ### Technical Analysis `OPENALEXANDRIA_BASE_URL` is used as the destination for all requests without validating its scheme, hostname, port, embedded user information, or trust relationship. Authenticated command ...[truncated 2079 chars]
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:47
Finding

Routine submission guidance can upload unreviewed sensitive research content

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Note
Location
openalexandria_cli.py:117
Finding

API keys supplied through command-line arguments may leak through local process metadata

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
90% confidence
Finding

The skill advertises and encourages use of a Python client that performs network access and uses environment-provided API credentials, but the manifest does not declare any explicit tool scope or allowed-tools restrictions. In an agent framework, this weakens least-privilege controls and can allow broader-than-expected access to network, environment variables, and local files, increasing the chance of credential exposure or unintended outbound requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The submit command sends JSON payload data to a remote /v1/submit endpoint using an API key, which may transmit user-provided content or system-derived data off-host. In this code file, there is no confirmation prompt, print/log disclosure at send time, or explicit warning text in the command help describing that bundle contents will be uploaded to a remote service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
77% confidence
Finding

The whoami command sends the provided API key to a remote endpoint for validation, but the code does not display any notice at execution time beyond the command name. Although network access is inherent to a CLI like this, the file itself provides no explicit warning or disclosure that credential-bearing requests are made to the configured server.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.