The Agent Skills Directory

[NO_CODE]: The skill is comprised entirely of Markdown files (SKILL.md and four reference documents) containing instructional text and frameworks. No executable scripts, binaries, or automation logic are included in the package, eliminating risks associated with malicious code execution.
[PROMPT_INJECTION]: The skill's primary workflow (Step 1 in SKILL.md) involves gathering context from external sources, including recent messages and user notes. This creates a surface for indirect prompt injection (Category 8), as instructions hidden in those external data sources could theoretically influence the AI's behavior. However, the risk is assessed as low because the skill lacks any functional capabilities (such as file-writing or network requests) that could be exploited. No boundary markers or sanitization procedures are defined in the instructions to mitigate this vulnerability.

communication