The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown instructions and templates. No scripts, binaries, or executable code are included in the skill package.- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided text describing a decision or situation (SKILL.md). While this input is untrusted, the skill's capabilities are limited to producing markdown tables and strategic options. It lacks dangerous capabilities like file system access, network connectivity, or command execution. The ingestion point is the user prompt, and while boundary markers are absent, the risk is negligible due to the low capability tier.- [DATA_EXPOSURE_AND_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file path access, or network exfiltration patterns was found.- [REMOTE_CODE_EXECUTION]: The skill does not contain any patterns for downloading or executing remote code. All external references are for documentation and academic grounding.

think-swot