agentworld
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: Fetches data from public API endpoints at agentworld.me to provide live updates on the agent economy, which is the primary purpose of the skill.
- [COMMAND_EXECUTION]: Uses curl to perform network requests to external API endpoints for data retrieval.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external API endpoints, which creates a theoretical surface for indirect prompt injection. However, the risk is minimal as the skill does not possess dangerous capabilities like file writing or executing commands based on the ingested data. 1. Ingestion points: External API responses from agentworld.me specified in SKILL.md. 2. Boundary markers: Not present; the agent is instructed to lead with numbers and context from the live feed. 3. Capability inventory: The skill uses curl for data retrieval but has no capabilities for file modification, persistent storage, or secondary network requests. 4. Sanitization: No specific sanitization or schema validation of API responses is performed within the instruction set.
Audit Metadata