The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional markdown and evaluation data. It does not include any scripts, executables, or configuration files that perform system operations. The instructions focus on marketing strategy, event planning, and performance measurement.
[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read external files (e.g., .agents/marketing-strategy.md, .agents/marketing-learnings.md) to gather context. While this creates a surface for indirect prompt injection if those files contain malicious instructions, the skill itself lacks any tools or capabilities (subprocess calls, file writes, or network operations) to exploit, rendering the risk negligible.
Ingestion points: .agents/marketing-learnings.md, .agents/marketing-strategy.md, .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md (identified in SKILL.md).
Boundary markers: Absent; the instructions do not specify delimiters or "ignore instructions" warnings for these external files.
Capability inventory: None; the skill contains no scripts or tool definitions that would allow for command execution or data exfiltration.
Sanitization: Absent; the skill does not define methods for filtering or validating the content of external files before ingestion.

experiential-marketing