The Agent Skills Directory

[SAFE]: The skill is a documentation framework designed to guide agents in writing and auditing technical content. It contains only Markdown files and does not include any executable scripts or binary files.
[PROMPT_INJECTION]: The skill uses directive language in SKILL.md and AGENTS.md to instruct the agent to prioritize this framework's specific rules over general training data. These are task-specific instructions and do not attempt to bypass safety guardrails or override system-level constraints.
[EXTERNAL_DOWNLOADS]: The skill references established industry resources from trusted organizations including Google, Stripe, and Canonical for informational purposes. These are standard documentation references and do not involve downloading or executing remote code at runtime.
[DATA_EXFILTRATION]: No patterns associated with credential harvesting, sensitive file access, or unauthorized network operations were identified. The examples provided in the documentation (e.g., API keys, callback URLs) use generic placeholders or testing-only values.
[COMMAND_EXECUTION]: The skill does not suggest or facilitate the execution of arbitrary shell commands or subprocesses. The code snippets included in the documentation are for illustrative purposes and intended to be used as documentation examples for the user.
[INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing user-provided content into documentation. While this is an ingestion point for potentially untrusted data, the skill does not grant the agent dangerous capabilities (such as file-system writes or network access) that would enable exploitation of this surface.

diataxis-docs-framework