The Agent Skills Directory

[PROMPT_INJECTION]: No instructions attempting to override agent safety guidelines, bypass filters, or extract system prompts were detected. The use of emphatic language (e.g., 'IMPORTANT', 'CRITICAL') is purely instructional and relates to the writing process.
[DATA_EXFILTRATION]: The skill does not contain any network-related commands (curl, wget) or patterns that access sensitive files or environment variables. No hardcoded credentials were found.
[REMOTE_CODE_EXECUTION]: There are no patterns involving the download or execution of external scripts, nor any use of package managers like npm or pip.
[COMMAND_EXECUTION]: No shell commands, subprocess spawning, or system-level operations are present in the skill files.
[OBFUSCATION]: All content is provided in plain-text markdown and YAML. No Base64, hex encoding, or hidden characters were found.
[DYNAMIC_EXECUTION]: The skill does not generate or execute code at runtime. It focuses exclusively on text-based prose generation and revision.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided essay drafts (untrusted data), it lacks the capabilities (such as code execution or network access) that would make such an injection exploitable. It is a low-risk text transformation skill.

write-theory-essays