codex-cli-docs
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill possesses an indirect prompt injection surface (Category 8) due to its core function of ingesting and processing documentation from external sources.
- Ingestion points:
scripts/core/scrape_docs.py(fetches remote content) andscripts/core/find_docs.py(retrieves indexed content for the agent). - Boundary markers: The documentation body is presented to the agent without explicit delimiters or instructions to disregard embedded commands.
- Capability inventory: The skill allows
Bashtool usage and performs file system writes and network requests viasubprocessandrequests. - Sanitization: It uses
BeautifulSoupandmarkdownifyto convert content from HTML to markdown, but does not filter for natural language instructions that could influence agent behavior. - [COMMAND_EXECUTION]:
scripts/utils/script_utils.pycontains logic to automatically install thepyyamlpackage viapipusingsubprocess.check_callif it is not found in the environment. - [EXTERNAL_DOWNLOADS]:
scripts/core/scrape_docs.pyfetches documentation content and indices fromdevelopers.openai.com, which is a well-known service owned by OpenAI.
Audit Metadata