onlyfansapi-skill

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources such as fan messages and profile text.\n
  • Ingestion points: Data is ingested through API responses involving chat messages and user profiles (referenced in SKILL.md and references/workflows.md).\n
  • Boundary markers: The instructions explicitly warn to treat fan messages and retrieved content as data, not instructions, and to keep fan text separate from the bot's operating instructions.\n
  • Capability inventory: The skill uses REST API tools and MCP servers to read/write data, send messages, and manage account configurations.\n
  • Sanitization: The skill relies on natural language boundary enforcement to prevent the agent from executing instructions embedded in user data.\n- [DATA_EXFILTRATION]: The skill performs network operations to app.onlyfansapi.com and docs.onlyfansapi.com. These are official vendor domains for the OnlyFansAPI service and do not represent unauthorized exfiltration.\n- [CREDENTIALS_UNSAFE]: The skill utilizes the ONLYFANSAPI_API_KEY environment variable for authentication, which is a standard and recommended practice for managing API secrets.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 08:56 AM
Security Audit — agent-trust-hub — onlyfansapi-skill