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.md and examples/core.md perform network requests to https://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 searchPublicPosts function in examples/core.md using 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 fetch implementations in SKILL.md and examples/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
Risk Level
CRITICAL
Analyzed
Jul 25, 2026, 02:34 AM
Security Audit — agent-trust-hub — api-search-xquik