The Agent Skills Directory

[SAFE]: The skill is composed of informational markdown files and JSON evaluation data. No instances of obfuscation, hardcoded credentials, or unauthorized data access were found.
[NO_CODE]: No executable code, such as Python, JavaScript, or shell scripts, is included in this skill's files.
[PROMPT_INJECTION]: The skill instructs the agent to read external context files, which constitutes a surface for indirect prompt injection. However, since the skill has no actionable tools, this surface does not present a significant risk.
Ingestion points: Reading from .agents/product-marketing-context.md or .claude/product-marketing-context.md as described in SKILL.md.
Boundary markers: No explicit delimiters or instructions are used to separate ingested content from system instructions.
Capability inventory: No dangerous capabilities (e.g., shell access, file-writing, or network requests) are provided or utilized by this skill.
Sanitization: The skill does not implement any validation or sanitization for the ingested context data.

free-tool-strategy