Security audit
Security checks for vulnerabilities and agentic risk
The skill appears to do what it says: send a DHL tracking number to DHL, retrieve status data, and format it for the user.
Install only if you are comfortable with the skill sending entered DHL tracking numbers to DHL's website endpoint. It does not appear to read local private data or persist itself, but it depends on an undocumented DHL endpoint and may stop working or conflict with DHL's site access rules.
The skill instructs use of shell and outbound network access but does not declare any explicit tool scope or permissions boundaries. That omission weakens policy enforcement and can allow an agent runtime to grant broader capabilities than users or reviewers expect, especially since the skill targets an undocumented internal DHL endpoint and suggests header variation to bypass anti-bot controls.
The function defaults to lang="de", and the surrounding docstrings and output strings are all in German, with no option or documented choice for other languages. This creates a locale/language policy issue because the skill imposes a specific language without explicit user opt-in or a justified region-specific constraint.
The skill's stated purpose is limited to tracking DHL parcels and formatting their status. Importing subprocess introduces process-execution capability that is not used anywhere in the file and is not justified by the manifest-described behavior.
This code performs an HTTP request to DHL and includes the user-provided tracking number in the request URL, which transmits user data to an external service. Although the function has a technical docstring, there is no user-facing prompt, warning, or visible disclosure in the script output that the tracking number will be sent over the network.
The script sets LANG to de by default, which forces a specific locale when the user does not provide a language argument. This is a natural-language policy concern because the skill does not offer an explicit language choice before applying the German default.
No suspicious patterns detected.
