Security audit
Security checks for vulnerabilities and agentic risk
This skill is a disclosed compliance guidance tool with a small regulations lookup script; no hidden persistence, credential access, or destructive behavior was found.
Install only if you want Chinese-outbound compliance guidance. Treat results as a checklist and risk triage, not legal advice; verify current laws with qualified counsel. The regulations lookup uses an external API, so do not submit confidential or personal data to any web/API endpoint unless you accept that third-party trust boundary.
A second, broader description-behavior mismatch indicates the skill presents itself as a comprehensive compliance auditor while apparently only fetching or displaying regulation data. This can cause operators to rely on the skill for legal-risk decisions, cross-border transfer assessments, and remediation planning that are not actually generated, creating a high-risk false sense of assurance.
A second, broader description-behavior mismatch indicates the skill presents itself as a comprehensive compliance auditor while apparently only fetching or displaying regulation data. This can cause operators to rely on the skill for legal-risk decisions, cross-border transfer assessments, and remediation planning that are not actually generated, creating a high-risk false sense of assurance.
The skill advertises executable shell capability via scripts/regulations.sh but does not declare any permissions or allowed-tools scope. That creates an execution-surface mismatch: a host agent may invoke shell functionality without users or policy layers having a clear, explicit declaration of what can run, reducing transparency and weakening least-privilege controls.
The trigger list includes very broad phrases such as general compliance, privacy, and international launch terms, making accidental activation more likely in unrelated conversations. Over-broad invocation increases the chance that the skill captures ordinary user queries, prompts unnecessary external lookups or script suggestions, and expands exposure to any unsafe behavior or misleading outputs.
The skill advertises a real API backend and an executable script without prominently disclosing that using them may transmit data to a third-party endpoint or execute local commands. In a compliance-focused skill, that omission is especially problematic because users may input sensitive business or personal data while assuming the check is local, creating privacy, confidentiality, and consent risks.
This markdown file contains user-facing natural-language guidance exclusively in Chinese, and there is no indication that the user can opt into this locale or that the document is restricted to a Chinese-language audience. Under the policy rule for language/locale constraints, forcing a specific language without user opt-in is a natural-language policy concern.
The script emits fixed Chinese strings such as "罚款上限" and "核心法规" regardless of user preference, with no opt-in or locale selection mechanism. This is a natural-language policy issue because it enforces a specific language in user-facing output without offering a language choice or justification.
The script makes outbound HTTP requests with curl to a remote API endpoint, but it provides no confirmation prompt, logging, print statement, comment, or docstring disclosing that market input will be sent to an external service. For a code file, this is a missing user warning about network transmission.
No suspicious patterns detected.
