edit-config
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches configuration templates, plugin metadata, and installation instructions from the author's repository at
https://github.com/Mizoreww/awesome-agent-config.gitto perform updates and maintenance. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and follows instructions from markdown files hosted in a remote repository to drive its internal logic for installation and configuration updates.
- Ingestion points: Remote files including
INSTALL.md,catalog.md,MAINTAIN.md, and platform-specific READMEs are read from the resolved GitHub branch. - Boundary markers: Absent. The instructions do not define specific delimiters or instructions to isolate the remote content from the agent's primary operating instructions.
- Capability inventory: The skill is authorized to modify agent configuration directories (
CLAUDE_CONFIG_DIR,CODEX_HOME), write tracking files (selection.json,files.json), and install native plugins or Model Context Protocol (MCP) components. - Sanitization: Absent. There is no mention of filtering, escaping, or validating the content of the remote markdown files before the agent acts upon them.
- [COMMAND_EXECUTION]: The skill performs shell-level operations including git commands to fetch branches and resolve commit SHAs, as well as file system modifications to update configurations and installation receipts.
Audit Metadata