The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses sed and rg (ripgrep) to inspect files in the ~/Projects/codex directory, which involves executing shell commands to read and search local file contents.
[PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it ingests untrusted data from local project files into the agent's context. 1. Ingestion points: ~/Projects/codex/codex-rs/AGENTS.md, ~/.codex/config.toml, and source files in codex-rs/. 2. Boundary markers: There are no delimiters or instructions to ignore embedded prompts within the ingested files. 3. Capability inventory: The skill has the capability to read file contents using sed and search them using rg. 4. Sanitization: No sanitization or validation is performed on the content read from the files.

codex-debugging