The Agent Skills Directory

[No Code] (SAFE): The skill consists exclusively of static Markdown content (SKILL.md and references/example.md). No scripts (Python, JavaScript, Bash), configuration files for package managers, or binary executables are present.
[Prompt Injection] (SAFE): Analysis of the metadata and instructions reveals no attempts to override system prompts, bypass safety filters, or extract system instructions. The content is strictly limited to retention diagnosis logic.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file path references, or network-bound commands (like curl or fetch) were detected.
[Indirect Prompt Injection] (SAFE): While the skill is intended to process user-supplied data regarding retention, it lacks any functional capabilities (such as subprocess execution, file writing, or network access) that could be leveraged by an attacker through malicious input data.

retention-drop-diagnoser