The Agent Skills Directory

[SAFE]: The skill is entirely instructional and does not contain any executable scripts, binaries, or configuration files that could pose a security risk.
[NO_CODE]: No code was found in the analyzed files. The skill relies exclusively on the language model's inherent reasoning and text generation capabilities.
[PROMPT_INJECTION]: The instructions do not contain patterns for bypassing safety guardrails or overriding system prompts. The language used is standard for academic writing guidelines.
[DATA_EXFILTRATION]: There are no network operations, API calls, or file system access patterns that could facilitate data exfiltration. The skill explicitly states it is a pure text processing skill.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to process user-provided academic context, it lacks the necessary capabilities (such as network access or command execution) to act upon malicious instructions embedded in that data.

image-description