tweetclaw

Fail

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: CRITICALCREDENTIALS_UNSAFEDATA_EXFILTRATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [CREDENTIALS_UNSAFE]: The skill requires users to configure a sensitive API key (XQUIK_API_KEY) which is then transmitted to the xquik.com domain.
  • [DATA_EXFILTRATION]: Automated security scanning has identified xquik.com and its associated API endpoints as phishing URLs. The skill facilitates the transmission of user-provided credentials to this flagged external service.
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves untrusted data from external sources such as X/Twitter tweets, profiles, and responses using curl and WebFetch.
  • Ingestion points: External data is ingested through various API endpoints such as /x/tweets/search and /x/users/{username} in SKILL.md.
  • Boundary markers: The instructions lack delimiters or specific warnings to ignore instructions embedded within the retrieved social media content.
  • Capability inventory: The skill utilizes Bash(curl:*) and WebFetch for data retrieval and interaction.
  • Sanitization: There is no evidence of sanitization, filtering, or validation of the retrieved content before it is processed by the agent.
Recommendations
  • AI detected serious security threats
  • Contains 4 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 9, 2026, 03:48 AM
Security Audit — agent-trust-hub — tweetclaw