T09 · Insecure Skill Coding Practices
- Location
scripts/imagegen.py:89- Finding
Credential Disclosure and Unrestricted Network Access Through Configurable Endpoints
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill is mostly a disclosed AI-HIVE content and image-generation helper, but its executable client handles API keys, custom endpoints, uploads, downloads, and output files in ways that deserve manual review before installation.
Review this before installing if you will use a real AI-HIVE account. Use only the default trusted AI-HIVE endpoint, do not accept commands that set a custom base URL, keep the API key limited and revocable, upload only files you intend to send to AI-HIVE, and choose a non-sensitive output directory because result filenames and downloads are not strongly constrained.
scripts/imagegen.py:89Credential Disclosure and Unrestricted Network Access Through Configurable Endpoints
scripts/imagegen.py:396Arbitrary File Write Through Unsanitized Task Metadata
scripts/imagegen.py:7Unpinned Third-Party Dependency Installation
The documented behavior understates and mischaracterizes the actual operational scope by omitting generic AI-HIVE capabilities such as model enumeration, chat, video generation, user-info/wallet queries, uploads, and task polling. Undeclared networked and account-scoped actions are security-relevant because they may surprise operators, trigger billable operations, expose account metadata, or broaden the blast radius beyond the claimed GEO/AEO auditing use case.
The documented behavior understates and mischaracterizes the actual operational scope by omitting generic AI-HIVE capabilities such as model enumeration, chat, video generation, user-info/wallet queries, uploads, and task polling. Undeclared networked and account-scoped actions are security-relevant because they may surprise operators, trigger billable operations, expose account metadata, or broaden the blast radius beyond the claimed GEO/AEO auditing use case.
The published skill identity promises GEO/AEO diagnosis and optimization, but the implementation exposes a generic AI Hive image-generation, upload, and task client with a fixed image model. This capability mismatch can mislead operators into granting broader access than intended and allows the skill to be used for unrelated content generation workflows, increasing the risk of policy bypass and unauthorized use under a trusted diagnostic label.
The skill advertises executable workflows and shell commands that imply access to environment variables, files, network, and local execution, but it does not declare any explicit tool scope or permissions boundaries. This creates an overbroad/implicit capability surface: a host agent may grant more access than users expect, increasing the chance of unintended secret exposure, file access, or network actions when the skill is invoked.
The display name and short description describe a very broad capability spanning workflow design, executable commands, and deliverable content, which overlaps with common writing, SEO, and marketing-help requests. In combination with implicit invocation, this ambiguous scope increases the chance the skill is selected outside its intended context, potentially leading to inappropriate automation or assistance on borderline deceptive promotional tasks.
The skill enables implicit invocation without any trigger constraints, so it may auto-activate on broad, ordinary content requests that only partially match its purpose. Because this skill can generate runnable workflows and AI-HIVE commands for marketing and content operations, unintended activation could cause overbroad tool use, user confusion, or unsafe assistance in adjacent high-risk content scenarios.
The skill's exposed generate pathway forwards arbitrary prompts to a remote image-generation API even though the surrounding skill context is framed as GEO content diagnosis. That disconnect makes the tool easier to repurpose for general image creation, including questionable marketing or misleading asset production, under the cover of a benign-sounding analysis skill.
This code embeds a Chinese-only skill name/description in natural-language strings, including the module docstring and argparse description, without any indication that users can choose another language or locale. Under the policy, forcing a specific language without user opt-in is a natural-language policy concern.
This code file contains natural-language descriptions and CLI guidance entirely in Chinese, starting from the module docstring and continuing through user-facing help text. Because the skill does not offer any language or locale selection or document a justified locale restriction, it can violate a language-choice policy for general-purpose skills.