The Agent Skills Directory

[NO_CODE]: The skill is entirely composed of Markdown text and instructions for the AI model. There are no associated scripts, executables, or configuration files that could perform actions outside of text generation.
[SAFE]: No malicious patterns, such as direct prompt injection, credential harvesting, or data exfiltration, were found within the provided instructions.
[PROMPT_INJECTION]: The skill processes external data (user conversation history), which creates a surface for indirect prompt injection. Ingestion points: 'conversations' field in the input JSON defined in SKILL.md. Boundary markers: Absent. Capability inventory: None (the skill lacks tools, network access, or file-system permissions). Sanitization: Absent. Due to the complete absence of actionable capabilities, this vulnerability surface does not pose a functional risk.

daily-review