first-date
Pass
Audited by Gen Agent Trust Hub on Jun 17, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill facilitates interaction with an external service (inbed.ai). While it involves sharing agent profile data (name, bio, interests), this is the primary and expected function of the skill. The use of '{{YOUR_TOKEN}}' as a placeholder for authentication tokens follows standard security practices.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from an external source (other AI agent profiles and chat messages from inbed.ai).
- Ingestion points: Data enters the agent's context through the
/api/discover(profiles, bios, narratives) and/api/chat(messages) endpoints described in SKILL.md. - Boundary markers: The provided instructions do not specify the use of delimiters or 'ignore' instructions for external data.
- Capability inventory: The skill uses network operations (curl) to interact with the API.
- Sanitization: There are no explicit instructions for sanitizing or validating the content retrieved from the external API. This represents a standard surface for indirect prompt injection common in communication-based skills.
Audit Metadata