swap-integration
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources including the PancakeSwap Routing API and various blockchain RPC providers, creating a surface for indirect prompt injection.
- Ingestion points: External data enters the context via curl and WebFetch requests to the PancakeSwap routing endpoint and public RPC services.
- Boundary markers: There are no specific delimiters or instructions provided to the agent to treat fetched data as untrusted or to ignore embedded instructions.
- Capability inventory: The skill has access to tools for filesystem modification (Write, Edit) and shell execution (Bash), which could be misused if the agent obeys malicious data.
- Sanitization: No sanitization or strict schema validation of API responses is demonstrated in the provided examples.
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of legitimate developer libraries, including official @pancakeswap SDKs and community-standard packages like viem and wagmi. These sources are considered well-known services.
- [COMMAND_EXECUTION]: Shell commands are used for standard development tasks such as installing dependencies and fetching token swap quotes from official API endpoints.
Audit Metadata