T09 · Insecure Skill Coding Practices
- Location
skill.py:46- Finding
Spoofable Trusted-Domain Classification
- Content
View full analysis
- Remediation
View remediation
Security audit
Security checks for vulnerabilities and agentic risk
This is a simple search helper that contacts Bing or DuckDuckGo as advertised, with privacy and result-labeling caveats but no hidden persistence or destructive behavior.
Install only if you are comfortable sending search queries to Bing or DuckDuckGo. Avoid using it for secrets, credentials, private project names, or sensitive personal data, and treat its official or quality labels as heuristic rather than verified trust signals.
skill.py:46Spoofable Trusted-Domain Classification
The skill advertises and requires network-capable components but does not declare any explicit tool scope or permissions boundary in the manifest. This can lead to overbroad network access expectations, weak reviewability, and accidental use in environments where users or hosts are not clearly informed that external requests will occur.
The documentation does not warn users that their search terms will be transmitted to third-party search engines, which may expose sensitive prompts, internal project names, or personal data. In agent contexts, users may reasonably assume local processing unless outbound disclosure is clearly disclosed, making this a real privacy and data-handling issue.
The description states that Chinese queries go to Bing and English queries go to DuckDuckGo, making language detection drive behavior automatically. This is a language/locale-based policy decision presented as default behavior without user opt-in at the point of use, which fits the natural-language policy violation criteria.
The file’s natural-language description states that Chinese searches go to Bing and English searches go to DuckDuckGo by default, and the code implements this behavior automatically. This is a language/locale-based policy choice applied without explicit user opt-in, which matches the natural-language policy violation criteria.