iblai-api-login
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDATA_EXFILTRATION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill requires the agent to navigate to and read content from external vendor websites (login.iblai.app/me) to extract organization keys and usernames. This creates a surface where malicious instructions could be embedded in the web content to potentially manipulate the agent's behavior.
- Ingestion points: Content rendered on the login.iblai.app/me page and browser localStorage.
- Boundary markers: None specified in the instructions to delimit external data from agent instructions.
- Capability inventory: The skill can perform network requests (curl, POST), access browser sessions, and write to local configuration files (.env, iblai.env).
- Sanitization: No explicit sanitization or validation of the ingested web content is described.
- [DATA_EXFILTRATION]: The skill is designed to handle and store sensitive Platform API Tokens and organization credentials. It communicates with vendor-owned domains (api.iblai.app) to mint and verify these tokens. While it follows safe practices by instructing the agent to store these in .env files and ensure they are gitignored, the handling of plaintext secrets is an inherent part of its credential management function.
Audit Metadata