gate-exchange-launchpool
Fail
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: HIGHEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill downloads the gate-cli binary from the vendor's official GitHub repository (github.com/gate/gate-cli) as part of its setup process. This is a vendor-owned resource used for primary functionality.
- [COMMAND_EXECUTION]: The skill invokes various gate-cli cex launch commands to interact with the Gate exchange for project discovery and transaction management.
- [PRIVILEGE_ESCALATION]: The setup.sh script includes a fallback mechanism that uses sudo install to install the CLI binary into /usr/local/bin if the local directory is not writable.
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data returned from exchange API calls (such as project names or record details) which can serve as a vector for indirect prompt injection. * Ingestion points: Data returned by gate-cli cex launch projects, pledge-records, and reward-records (referenced in SKILL.md). * Boundary markers: No delimiters or specific instructions are provided to the model to ignore potential instructions embedded in the API output. * Capability inventory: The skill possesses write capabilities through gate-cli cex launch pledge and redeem commands (referenced in SKILL.md). * Sanitization: No sanitization or validation logic is defined for the external data ingested into the prompt context.
Recommendations
- AI detected serious security threats
Audit Metadata