The Agent Skills Directory

[PROMPT_INJECTION]: No malicious injection patterns or attempts to override safety guidelines were detected. The skill uses instructional language consistent with its purpose as a documentation tool.
[DATA_EXFILTRATION]: The skill does not access sensitive files or perform network operations. It references standard project files like package.json and SKILL.md for organization, which is expected behavior for a development assistant.
[REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill mentions package managers and scripts in a purely instructional context, providing examples of how to document them in a skill.
[DYNAMIC_CONTEXT_INJECTION]: While the skill documents the platform's ability to inject dynamic context via shell commands, it does not execute any shell commands itself. All references to this feature are links to official documentation for developer awareness.
[OBFUSCATION]: No obfuscated content, Base64 encoding, zero-width characters, or homoglyphs were detected in the skill's instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill has a data ingestion surface as it processes user drafts or notes to generate documentation. However, this is the primary purpose of the skill, and the risk is mitigated by the structured nature of the requested output (SKILL.md format).

document-skills