The Agent Skills Directory

[SAFE]: The skill does not contain any executable scripts, binary files, or command execution patterns. All logic is strictly instructional markdown and YAML configuration metadata.- [NO_CODE]: The provided files (SKILL.md and agents/openai.yaml) consist entirely of text-based instructions and platform-specific settings without any accompanying code or dependencies.- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external data sources such as official specifications, project documentation, and source code. This represents a potential surface for indirect prompt injection if those external files contain malicious instructions. However, the skill lacks any capabilities (such as file-writing, network exfiltration, or shell access) to act on such instructions, and its output is strictly advisory counsel. Ingestion points: SKILL.md (Step 3: Primary source research against specifications and repository source). Boundary markers: The skill uses an authority order but lacks explicit delimiters for external content. Capability inventory: None detected. Sanitization: None present.

akowe