codex-debugging
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFE
Full Analysis
- [DATA_EXPOSURE]: The skill instructs the agent to read the local configuration file at
~/.codex/config.toml. While this involves accessing a configuration file, it is standard practice for a debugging skill and does not involve exfiltration to external services. - [INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it reads local source files (e.g.,
codex-rs/AGENTS.md) and configuration files. - Ingestion points:
codex-rs/AGENTS.md,~/.codex/config.toml, and source files within thecodex-rs/directory. - Boundary markers: None identified in the provided instructions.
- Capability inventory: Uses
sed,rg(ripgrep), and directory navigation (cd) to read and search local files. - Sanitization: No explicit sanitization or filtering of the file contents before processing is mentioned.
Audit Metadata