The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown-based instructions and metadata. No malicious code, obfuscation, or unauthorized access patterns were detected.
[INDIRECT_PROMPT_INJECTION]: The skill documentation suggests reading a local configuration file .agents/marketing-context.md.
Ingestion points: The file .agents/marketing-context.md is identified as an input source in SKILL.md.
Boundary markers: No explicit delimiters or boundary markers are defined for this input.
Capability inventory: The skill does not define any executable capabilities, network operations, or file-system writing tools that could be abused via prompt injection.
Sanitization: No input validation or sanitization routines are specified for the ingested content.

attribution