Back to skill

Security audit

Byted Viking Knowledgebase

Security checks for vulnerabilities and agentic risk

Overview

This skill has a coherent knowledge-base search purpose, but it sends the API bearer key and user queries over plaintext HTTP.

Review before installing. Use this only in an isolated environment with least-privileged, rotating Viking credentials, and do not send sensitive queries until the transport is changed to HTTPS and dependencies are pinned.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/search.py:29
Finding

Bearer API Key and Knowledge Queries Transmitted over Plaintext HTTP

Content
View full analysis
Remediation
View remediation

T08 · Insecure Dependencies

Warning
Location
scripts/requirements.txt:1
Finding

Unpinned and Incomplete Third-Party Dependency Specification

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Findings (10)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
94% confidence
Finding

The skill invokes code with access to environment variables and network resources but does not declare any explicit tool scope or permission boundary. In an agent setting, this increases the risk of over-privileged execution, unintended secret exposure, or network access being granted implicitly when the skill is triggered.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill is configured as a default handler whenever the user mentions a knowledge base, which is an overly broad trigger. This can cause the agent to invoke networked code and access configured credentials in situations where the user did not clearly intend to use this external service.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The manifest description is written as an instruction in Chinese that defaults handling to this skill when the user mentions the topic, but it does not offer any language or locale choice. This can violate language/locale policy if the skill implicitly assumes Chinese-only interaction without user opt-in or documented regional justification.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
99% confidence
Finding

The request is explicitly configured to use HTTP (set_shema("http") and url="http://...") while sending a bearer token and user query in transit. This allows network attackers or intermediaries to intercept or modify credentials and knowledge-base content, which is especially risky because the skill is specifically intended to handle user knowledge-base queries.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

User search queries are sent over plain HTTP without any disclosure, so sensitive prompts or proprietary knowledge-base requests can be exposed to passive observers or tampered with in transit. In this skill context, that is more dangerous because the entire purpose of the skill is to submit potentially business-sensitive knowledge-base queries to a remote service.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
84% confidence
Finding

The documentation instructs operators to provide API key and secret environment variables but does not include guidance on secure handling, least privilege, masking, or avoiding disclosure in prompts/logs. While not an exploit by itself, this increases the chance of accidental credential exposure during use or troubleshooting.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
93% confidence
Finding

The dependency 'volcengine' is unpinned, so installations may resolve to different versions over time, including releases with breaking changes or newly introduced vulnerabilities. This weakens build reproducibility and supply-chain control, even though the file itself does not prove a currently exploitable flaw.

Content

Scanner excerpt · scripts/requirements.txt (reported line 1)May include surrounding context.

text
volcengine
aiohttp

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
98% confidence
Finding

The dependency 'aiohttp' is unpinned, which means the environment may install an unpredictable version at deploy time. Because aiohttp has a history of security advisories, leaving it unpinned increases the chance of pulling an affected release or introducing unreviewed changes into a network-facing component.

Content

Scanner excerpt · scripts/requirements.txt (reported line 2)May include surrounding context.

text
volcengine
aiohttp

Unverifiable Dependency: aiohttp has 16 known advisory(ies) (CVE-2024-52303 (aiohttp has a memory leak when middleware is enabled when requesting a resource ); CVE-2026-54279 (aiohttp: Host-Only Cookies Become Domain Cookies After CookieJar Persistence); CVE-2026-34514 (AIOHTTP has CRLF injection through multipart part content type header constructi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
95% confidence
Finding

The manifest includes 'aiohttp' without a version, while the package has multiple known advisories across releases. Because the installed version cannot be verified from this file, there is a real supply-chain and patch-management gap: a vulnerable aiohttp version could be installed without visibility, especially important for a skill likely interacting with remote knowledgebase services over HTTP.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The manifest describes this skill as handling Viking knowledge-base operations when the user mentions a knowledge base. While calling the remote knowledge-base service is expected, explicitly reading credential material from environment variables is an additional capability not stated in the manifest and is not inherent from the user-facing description alone.

Content

No source excerpt is available for this finding.