Skill flagged — suspicious patterns detected

ClawHub Security flagged this skill as suspicious. Review the scan results before using.

必捷快递查询 Bijie Express

v1.0.0

Free package tracking for 2000+ couriers (SF, YTO, ZTO, Yunda, STO, JT, JD, EMS). Returns logistics status, location, transit nodes & ETA. 必捷免费快递查询,支持国内外2000...

0· 48·0 current·0 all-time
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Suspicious
high confidence
Purpose & Capability
The code and SKILL.md both implement courier tracking for many carriers and include an internal company-code list — this aligns with the description. However, the SKILL.md documents an HTTPS endpoint at https://www.bijieserv.com while the included script uses http://skill.bijieserv.com (different host and unsecured HTTP). This mismatch is unexpected and should be clarified.
!
Instruction Scope
SKILL.md instructs the agent to call the bijieserv API and to desensitize returned phone numbers. The Python script performs outbound HTTP POSTs to an external API and only desensitizes numbers when formatting display output. The script sends parameters (including 'phone') in the POST body and does not remove or mask PII before transmission. That contradicts the privacy-protection claim in SKILL.md. The script also uses an in-memory query_history for rate-limiting, which is ephemeral and not persisted as the SKILL.md's caching/limits language might imply.
Install Mechanism
There is no install spec and no binaries required. The skill is distributed as code files only (no automated downloads or third-party packages beyond standard Python requests), which keeps install risk low.
Credentials
The skill declares no environment variables or credentials and the code does not require or reference any external credentials. That is proportionate to its described purpose.
Persistence & Privilege
The skill is not force-enabled (always:false) and does not request elevated persistence. It only keeps an in-memory query_history; it does not modify other skills or system settings.
What to consider before installing
What to consider before installing: - Endpoint mismatch & encryption: SKILL.md lists an HTTPS endpoint (www.bijieserv.com) but the shipped script posts to http://skill.bijieserv.com. HTTP transmits data unencrypted and a different hostname may route requests to an unexpected server. Ask the author to confirm the correct, canonical API host and that HTTPS is used everywhere. - Privacy claims vs behavior: The README/skill promises automatic desensitization, but the code only masks phone numbers when formatting results for display — it still may send the raw phone (or other fields) to the remote API. If you plan to submit real phone numbers or sensitive addresses, be cautious. - In-memory rate limiting: The script's 'query_history' is ephemeral per process. If you rely on the skill's claimed 30-minute single-number protection to avoid carrier lockouts, verify whether that state is actually persisted across agent runs. - Verify provenance: There's no homepage or known publisher. If you need to trust this skill, request the full, untruncated source, confirm the correct API domain, and ideally test with dummy/non-sensitive tracking numbers first. - Mitigations: Prefer the skill only if the API endpoint is confirmed to be official and available over HTTPS. If you must use it before confirmation, avoid providing real phone numbers or other PII; use partial/masked values instead. If the author cannot justify the http:// skill.bijieserv.com host, treat the mismatch as a red flag and avoid sending sensitive data.

Like a lobster shell, security has layers — review code before you run it.

latestvk97c8g9rqxtd462qpntgw8mx5d83ggzf

License

MIT-0
Free to use, modify, and redistribute. No attribution required.

Comments