kopis-performance-search
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill utilizes npx to execute the author's package @nomadamas/k-skill@0 to fetch instructions and manage skill files, as described in SKILL.md. This is a mechanism for remote code retrieval and execution managed by the vendor.\n- [COMMAND_EXECUTION]: The skill performs curl requests to the vendor's proxy server (k-skill-proxy.nomadamas.org) to interact with the KOPIS API for performance and facility searches, as detailed in instruction.md.\n- [INDIRECT_PROMPT_INJECTION]: The skill handles data from the external KOPIS API via a proxy, creating an attack surface for indirect prompt injection. Findings: 1. Ingestion points: curl responses from k-skill-proxy.nomadamas.org in instruction.md. 2. Boundary markers: The skill instructions do not specify explicit delimiters or warnings for the agent to ignore instructions embedded in the API data. 3. Capability inventory: The agent has access to curl for network operations and npx for command execution. 4. Sanitization: No explicit sanitization or validation of the API data is defined in the instructions before processing.
Audit Metadata