The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external files to gain business context, which represents a potential attack surface for indirect prompt injection if those files contain malicious instructions.
Ingestion points: Reads content from .agents/marketing-strategy.md, .agents/marketing-learnings.md, and several legacy filenames like product-marketing-context.md (specified in SKILL.md).
Boundary markers: The instructions do not specify any delimiters or safety markers when reading these external files to differentiate data from instructions.
Capability inventory: The skill generates strategic recommendations, content outlines, and distribution plans based on the ingested context.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from these external files.
[SAFE]: The skill consists entirely of strategic guidelines, informational benchmarks, and evaluation templates. No executable code, remote downloads, obfuscation, or unauthorized system access patterns were detected.

lead-magnets