The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches real-time bridge metrics, chain support, and volume data from DeFiLlama's official API (bridges.llama.fi). DeFiLlama is a well-known service in the blockchain industry, and these network operations are strictly aligned with the skill's primary purpose.
[INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection as it ingests and processes untrusted data from an external API. However, the risk is negligible due to the structured nature of the data and the absence of dangerous system capabilities. Ingestion points: The _fetch_json function in bridge_comparison.py, bridge_monitor.py, bridge_risk_scorer.py, and route_optimizer.py retrieves external API responses. Boundary markers: No specific delimiters or safety instructions are used when interpolating external data into the agent's context. Capability inventory: The skill scripts are limited to network read operations (urllib.request). There are no capabilities for file writing, shell command execution (subprocess), or dynamic code evaluation (eval/exec). Sanitization: The skill relies on standard JSON parsing and does not apply additional sanitization or filtering to the API content.

bridge-analyzer