api-search-xquik
Fail
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: CRITICALDATA_EXFILTRATIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill requires and provides patterns for transmitting a user's 'XQUIK_API_KEY' to
https://xquik.com. Since this domain is flagged as a phishing site, this functionality directly exposes sensitive credentials to a potentially malicious third party. - [EXTERNAL_DOWNLOADS]: The skill instructions and code examples in
SKILL.mdandexamples/core.mdperform network requests tohttps://xquik.com/api/v1/x/tweets, which is a confirmed malicious URL (Phishing) according to automated security scans. - [PROMPT_INJECTION]: The skill processes data from the X platform, introducing an indirect prompt injection vulnerability.
- Ingestion points: Tweet content is ingested via the
searchPublicPostsfunction inexamples/core.mdusing the Xquik API. - Boundary markers: The skill uses natural language instructions in
SKILL.md(Philosophy and Red Flags sections) advising the agent to treat content as untrusted, but does not implement programmatic delimiters. - Capability inventory: The skill maintains active network access via
fetchimplementations inSKILL.mdandexamples/core.md. - Sanitization: The skill does not perform any programmatic sanitization or filtering of external content, relying entirely on the agent following behavioral guidelines to avoid executing embedded instructions.
Recommendations
- AI detected serious security threats
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata