The Agent Skills Directory

[SAFE]: No malicious patterns such as prompt injection, data exfiltration, or unauthorized command execution were identified in the skill instructions or metadata.
[INDIRECT_PROMPT_INJECTION]: The skill includes instructions to read external context files, which represents a standard data ingestion surface.
Ingestion points: The skill attempts to read .agents/product-marketing-context.md or .claude/product-marketing-context.md to inform its responses (SKILL.md).
Boundary markers: No specific delimiters or "ignore" instructions for the ingested content are defined.
Capability inventory: The skill contains no code execution (exec/eval), network operations, or file-writing capabilities.
Sanitization: No specific sanitization or validation of the ingested context file content is performed.

popup-cro