axelar
Pass
Audited by Gen Agent Trust Hub on Sep 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documents a wide range of CLI commands for the
axelardbinary, which allows for network interaction, transaction submission, and validator management. It provides templates for queries (e.g.,axelard query nexus chains) and transactions (e.g.,axelard tx multisig rotate). - [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill provides instructions and references derived from the external
axelar-corerepository. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to ignore potentially malicious commands embedded in data retrieved from the network or external docs.
- Capability inventory: The skill enables the agent to execute shell commands via the
axelardbinary, covering query, transaction, and validator signing operations. - Sanitization: The documentation does not specify sanitization or validation procedures for variables (like
$KEYor$NODE) used in the command templates.
Audit Metadata