The Agent Skills Directory

[PROMPT_INJECTION]: The skill defines a specific persona (Stephen King) for writing advice. It does not contain instructions to bypass safety filters, ignore system prompts, or override agent constraints. The instructions are focused on providing a specific perspective on writing discipline and style.
[REMOTE_CODE_EXECUTION]: No remote script downloads or piped command executions (e.g., curl|bash) were detected. The installation command provided in the README is standard for the platform and points to the vendor's own repository.
[DATA_EXFILTRATION]: The skill does not access sensitive system paths (~/.ssh, ~/.aws) or include commands to transmit data to external servers. It does not hardcode any credentials or API keys.
[OBFUSCATION]: The content is provided in clear text. There are no Base64-encoded payloads, zero-width characters, or homoglyph-based evasions in the instructions or examples.
[DYNAMIC_CONTEXT_INJECTION]: The skill does not use shell command interpolation syntax (!command) to execute code at load time.
[INDIRECT_PROMPT_INJECTION]: While the skill is designed to ingest and analyze user-provided text for critiques, it does not possess dangerous tools or capabilities (like file writing or network access) that could be exploited through malicious content in the processed data. The risk is inherent to all LLM applications and minimized by the lack of privileged capabilities.

stephenking-perspective