The Agent Skills Directory

[SAFE]: No security issues were detected. The skill consists of Markdown-based instructions and metadata that define a strategic reasoning framework.
[PROMPT_INJECTION]: The instructions do not contain any patterns intended to bypass safety guidelines, override system instructions, or extract system prompts. The language used is instructional and aligned with the stated purpose of decision evaluation.
[DATA_EXFILTRATION]: There are no commands or instructions involving sensitive file paths, credential harvesting, or network-based exfiltration. No hardcoded secrets were found.
[REMOTE_CODE_EXECUTION]: The skill does not download or execute external scripts. It does not use package managers (npm, pip) or shell-piping commands like curl | bash.
[OBFUSCATION]: No obfuscated content, Base64-encoded commands, zero-width characters, or homoglyph attacks were detected in the files.
[INDIRECT_PROMPT_INJECTION]: While the skill processes user-provided claims or strategies as input, it lacks the dangerous capabilities (e.g., file system writes, network calls, or code execution) required for an injection to be exploitable. The input is analyzed logically to produce a Markdown table.
[DYNAMIC_CONTEXT_INJECTION]: No use of the !command syntax was found in the SKILL.md or other project files.

think-what-would-have-to-be-true