T09 · Insecure Skill Coding Practices
- Location
scripts/search.py:29- Finding
Bearer API Key and Knowledge Queries Transmitted over Plaintext HTTP
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
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.
scripts/search.py:29Bearer API Key and Knowledge Queries Transmitted over Plaintext HTTP
scripts/requirements.txt:1Unpinned and Incomplete Third-Party Dependency Specification
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.
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.
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.
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.
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.
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.
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.
volcengine
aiohttp
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.
volcengine
aiohttp
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.
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.