The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes user-provided Markdown data which represents a surface for Indirect Prompt Injection. However, the skill only transforms this input into text for manual copying by the user and lacks dangerous capabilities like file writing or network access that would allow for exploitation. No direct prompt injection or safety bypass patterns were found.- [EXTERNAL_DOWNLOADS]: The skill references official Google and DeepMind documentation and a well-known community reference repository. These external links are informational and do not involve the download of executable code or unverified dependencies.- [DATA_EXFILTRATION]: No hardcoded credentials, sensitive file access (such as .ssh or .env), or unauthorized network operations were detected. All described workflows operate on user-provided session content within the intended scope.- [COMMAND_EXECUTION]: The skill does not execute arbitrary shell commands. It references internal vendor-specific utilities like ai-slop-reviewer, which is a safe and expected behavior for this author.- [REMOTE_CODE_EXECUTION]: No patterns of remote script execution or runtime code loading from untrusted sources were identified.

notebooklm-slide-prompt