The Agent Skills Directory

[SAFE]: The skill consists entirely of Markdown documentation and reference templates for marketing workflows. No scripts, binaries, or executable commands are present.
[NO_CODE]: There are no code files or automation scripts associated with this skill; it functions as a set of structured instructions and references for an AI agent.
[DATA_EXPOSURE]: The skill instructs the agent to read context from .agents/product-marketing-context.md if available. This is a standard pattern for context sharing in this environment and does not involve unauthorized data access.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection via the .agents/product-marketing-context.md file ingestion point.
Ingestion points: .agents/product-marketing-context.md (read in SKILL.md).
Boundary markers: Absent; the agent is simply told to read and use the context.
Capability inventory: No local scripts or tools are defined within the skill itself.
Sanitization: Absent.
Since the skill lacks autonomous write/network capabilities of its own, the risk remains low.

paid-ads