configure-ecc
Warn
Audited by Gen Agent Trust Hub on Jun 24, 2026
Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill clones a remote repository from an unverified third-party source (https://github.com/affaan-m/everything-claude-code.git) using git clone. This content is then used to install executable components (skills and rules) into the agent's local environment.
- [COMMAND_EXECUTION]: The skill executes multiple shell commands to manage files and directories, including rm -rf, mkdir -p, cp -r, and grep. It performs modifications within the user's home directory (~/.claude/) and project directories.
- [PROMPT_INJECTION]: As an installer for third-party instructions, the skill is subject to indirect prompt injection. Malicious instructions within the source repository could be installed into the agent's configuration, potentially influencing future behavior without direct user oversight. (Ingestion points: Files cloned from github.com/affaan-m/everything-claude-code at runtime; Boundary markers: None identified; Capability inventory: File system write access, file system read access, and in-place file editing; Sanitization: None identified).
Audit Metadata