The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read local context files (e.g., .agents/product-marketing.md) to inform its responses. This represents a potential surface for indirect prompt injection if those files contain untrusted content, though in this context, it is a standard method for providing project-specific information to the agent.
Ingestion points: SKILL.md prompts reading from .agents/product-marketing.md, .claude/product-marketing.md, or product-marketing-context.md.
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for these ingested files.
Capability inventory: The skill is primarily instructional and does not demonstrate capabilities for executing shell commands, writing files, or performing network operations.
Sanitization: No sanitization or validation of the context file content is performed.
[SAFE]: The skill consists of instructional content and references for marketing strategy. No malicious patterns, obfuscation, or unauthorized code execution were detected.

free-tools