The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from several external markdown files to gain context for its inventory recommendations. This creates a surface for indirect prompt injection where malicious instructions embedded in these data sources could influence the agent's behavior.
Ingestion points: The skill reads from .agents/marketing-learnings.md, .agents/marketing-strategy.md, marketing-strategy/references/brand-tier-guide.md, marketing-strategy/references/distribution-model-guide.md, and commercial-ops/references/retail-revops.md.
Boundary markers: There are no explicit boundary markers or instructions to treat the content of these files as untrusted data.
Capability inventory: The skill's capabilities are limited to providing analysis and delegating to other defined skills; it does not perform file writes, network operations, or execute shell commands.
Sanitization: No sanitization or verification of the external file content is performed before the data is incorporated into the agent's reasoning process.

overstock