agnix
Warn
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS] (MEDIUM): The skill prompts the installation of
agnix-cliviacargo install agnix-cli. The source repository (github.com/avifenesh/agnix) is not on the trusted list of providers, making it an unverifiable dependency. - [COMMAND_EXECUTION] (LOW): The skill invokes the
agnixbinary to perform file system operations (agnix .). While this is the stated purpose, it involves running a binary that performs file read and write operations on the user's project files. - [INDIRECT_PROMPT_INJECTION] (LOW):
- Ingestion points: The skill reads local configuration files such as
CLAUDE.md,SKILL.md, and.mcp.jsonduring validation processes. - Boundary markers: No delimiters or warnings for embedded instructions are present in the provided skill code.
- Capability inventory: Performs file read and write (via the
--fixflag) operations through a subprocess call to theagnixbinary. - Sanitization: The skill does not explicitly sanitize or escape the content of the files it processes, which could lead to unintended behavior if the files contain malicious instructions.
Audit Metadata