The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied content via the $ARGUMENTS variable to verify claims and justification chains. While the instructions do not specify explicit boundary markers or sanitization for this external data, the skill functions solely as a reasoning prompt. It does not possess capabilities such as network access, file system writes, or command execution that could be exploited by malicious content within the processed artifacts.
[EXTERNAL_DOWNLOADS]: The README documentation includes installation instructions and links to a .skill file hosted on the author's GitHub repository (github.com/synapseradio/ai-skills). These references are used for standard skill distribution and do not involve the execution of untrusted or third-party code within the skill's operational context.

integrity