The Agent Skills Directory

[SAFE]: The skill is composed exclusively of markdown documentation, copy templates, and strategic advice for marketers. No shell commands, automated scripts, or unauthorized network operations were identified within the skill structure or its reference files.
[INDIRECT_PROMPT_INJECTION]: The skill establishes an ingestion point for untrusted data by instructing the agent to read from .claude/product-marketing-context.md if it exists (SKILL.md). Ingestion point: local context file; Boundary markers: None; Capability inventory: No dangerous capabilities (file writes or network ops) are present to be exploited; Sanitization: None. Due to the lack of exploitable capabilities, this risk is minimal and consistent with intended agent usage.

paid-ads