T09 · Insecure Skill Coding Practices
- Location
scripts/main.py:16- Finding
Sensitive Input Is Transmitted to an External Service for Locally Performable Operations
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This skill performs the advertised conversions, but it sends all submitted content and an environment-based admin key to an external service for tasks that could be done locally.
Review this carefully before installing. Do not use it with passwords, tokens, private URLs, proprietary files, or regulated data unless you are comfortable sending that content to the external JieBang service and using the configured admin credential. A local-only implementation would be safer for these operations.
scripts/main.py:16Sensitive Input Is Transmitted to an External Service for Locally Performable Operations
The skill retrieves an admin credential from the environment and attaches it to every external API request, despite only offering basic text transformations. Using a privileged key for low-risk utility operations broadens the blast radius if the endpoint, logs, or surrounding service are compromised.
The skill is described as a local text/file processing utility, but it sends the full user-provided input to an external domain for hashing. This creates an undisclosed data exfiltration path for potentially sensitive text and violates user expectations that these simple operations occur locally.
The skill advertises externally backed processing but does not declare any explicit tool scope or permissions despite detected network and environment capabilities. This weakens least-privilege controls and makes it harder for reviewers and users to understand what the skill can access, increasing the risk of unintended outbound requests or broader data exposure if the implementation is modified or abused.
The skill description says it is based on an external API, but it does not clearly warn users that submitted text or file-derived content will be transmitted off-platform for processing. This creates a privacy and data-handling risk because users may provide secrets, personal data, or proprietary content under the assumption processing is local.
The module documentation claims the tool provides hashing, Base64, and URL functions directly, but the implementation is actually a proxy to an external API. This mismatch misleads reviewers and users about where their data goes and masks the real trust boundary.
The code sends raw user input to an external API without any user-facing warning, despite handling content that may include secrets, URLs with tokens, or confidential text. Lack of disclosure prevents informed consent and increases the risk of inadvertent sensitive-data leakage.
Base64 encoding/decoding is a local primitive, yet the code transmits all input to a remote API. Users may paste secrets, tokens, or files for conversion, so this behavior unnecessarily exposes sensitive content to a third party.
URL encoding/decoding can be safely performed locally, but this implementation sends user input to an external service. That creates unnecessary exposure of URLs, parameters, tokens, and other potentially sensitive data embedded in the input.
All user-facing natural-language content in the skill file is in Chinese, with no indication that the skill supports other languages or that Chinese is a justified locale-specific requirement. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.
The human-readable descriptions and user-facing strings are written only in Chinese, with no indication that the user can choose another language or locale. Under the policy rule, a skill should not impose a language/locale without opt-in unless the constraint is explicitly justified.
The script retrieves an admin key from an environment variable and injects it into the X-Admin-Key request header, but there is no user-facing notice that credentials are required and will be used for outbound authentication. This is a safety-relevant behavior under the warning criteria for code files because it accesses sensitive environment-based credentials silently.