The Agent Skills Directory

[PROMPT_INJECTION]: No override or bypass instructions were detected in the skill markdown. The instructions are focused strictly on content adaptation and follow a structured workflow without attempting to influence the agent's safety parameters.- [DATA_EXPOSURE_AND_EXFILTRATION]: The skill does not access sensitive system paths or credentials. There are no network tools (like curl or wget) enabled or requested, which prevents any form of data exfiltration.- [UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill does not attempt to install external packages (npm/pip) or execute remote scripts. It uses built-in tools for basic file manipulation.- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted blog content as its primary input. While this presents an ingestion surface, the risk is mitigated because the skill lacks high-privilege capabilities such as shell execution or network access, and its output is confined to text files in a local directory.- [DYNAMIC_CONTEXT_INJECTION]: The skill does not use the dynamic context injection syntax to execute shell commands at load time.

blog-repurpose