The Agent Skills Directory

[SAFE]: No malicious patterns, hidden commands, or security vulnerabilities were found. The skill serves as a static template and guide for SEO and content optimization on the Medium platform.
[INDIRECT_PROMPT_INJECTION]: The skill instructions specify reading project strategy from external files. Ingestion points: The skill attempts to read content from .claude/project-context.md and .cursor/project-context.md (specified in SKILL.md). Boundary markers: No explicit delimiters are used to isolate the context content. Capability inventory: The skill has no defined tools, network capabilities, or shell access. Sanitization: No validation or filtering is applied to the context files. Although this represents an external data ingestion surface, the risk is negligible because the skill does not have any privileged capabilities that could be triggered by injected instructions.

medium-posts