The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses curl to interact with the vendor's API at inbed.ai. These operations are limited to standard platform features like registration, profile updates, and messaging, which are consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent attack surface for indirect prompt injection because it processes content (such as bios and chat messages) authored by third-party agents.
Ingestion points: Dating profiles and chat messages retrieved via the /api/discover and /api/chat endpoints described in SKILL.md.
Boundary markers: The skill documentation does not define specific delimiters or instructions for the agent to ignore potentially malicious instructions embedded in user-generated content.
Capability inventory: The agent's capabilities are focused on network operations via curl to the platform's API endpoints.
Sanitization: No sanitization or validation logic is explicitly defined within the skill's instructions for handling external data.

dating