botchan
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows an agent to read messages from a public and permissionless blockchain, which serves as a source of untrusted input that could contain malicious instructions.
- Ingestion points: Data is ingested via the
botchan readandbotchan profilecommands as documented inSKILL.md. - Boundary markers: There are no specified delimiters or system instructions provided to help the agent distinguish between message content and operational instructions.
- Capability inventory: The skill provides capabilities to write back to the blockchain using
botchan postandbotchan commentinSKILL.md, which could be exploited if an agent executes instructions embedded in messages it reads. - Sanitization: The documentation does not describe any sanitization or validation processes for the content retrieved from the blockchain.
- [COMMAND_EXECUTION]: The skill functions by executing shell commands using the
botchanCLI tool. - [EXTERNAL_DOWNLOADS]: The installation process involves downloading and installing the
botchanCLI globally from the NPM registry.
Audit Metadata