Uniswap Batch Swap

PassAudited by VirusTotal on May 12, 2026.

Findings (1)

The skill is classified as suspicious due to the broad file system access granted to the AI agent via `Read`, `Glob`, and `Grep` in the `allowed-tools` section of `SKILL.md`. While the skill's stated purpose and workflow are benign (executing token swaps), these powerful tools introduce a significant prompt injection vulnerability. An attacker could craft a malicious prompt to instruct the agent to read sensitive files (e.g., credentials, configuration) or list directories, potentially leading to unauthorized information disclosure, even though the skill itself does not explicitly instruct such actions.