tikhub-api-helper
Fail
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: HIGHCREDENTIALS_UNSAFEDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- CREDENTIALS_UNSAFE (HIGH): A hardcoded API token (DEFAULT_TOKEN) is present in api_client.py. Storing credentials directly in code is a high-risk practice that can lead to unauthorized access.
- DATA_EXFILTRATION (LOW): The skill performs network operations using urllib to connect to api.tikhub.io and api.tikhub.dev. These domains are not in the trusted whitelist. While this is the primary purpose of the skill, it represents a data transmission vector to external sources.
- PROMPT_INJECTION (LOW): The skill is vulnerable to indirect prompt injection because it ingests and processes untrusted data from social media platforms (TikTok, Instagram, YouTube, etc.). 1. Ingestion points: API response data retrieved in api_client.py. 2. Boundary markers: Absent; there are no instructions for the agent to use delimiters or ignore embedded instructions in the fetched content. 3. Capability inventory: Ability to perform API searches and data retrieval. 4. Sanitization: Absent; the retrieved content is not sanitized or validated before being presented to the agent.
Recommendations
- AI detected serious security threats
Audit Metadata