The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read marketing context from local files, such as .agents/product-marketing.md or product-marketing-context.md, to tailor its conversion recommendations. This introduces a surface where malicious instructions embedded in those files could influence agent behavior.
Ingestion points: SKILL.md (Initial Assessment section)
Boundary markers: Absent; no specific delimiters or instruction-bypass warnings are defined for the ingested file content.
Capability inventory: File reading is the primary capability associated with this surface; no subprocess execution or network-send capabilities are linked to the data ingestion.
Sanitization: Absent; there are no instructions to validate or filter the content of the marketing context files.
[EXTERNAL_DOWNLOADS]: The skill references an external RevOps inbound-routing playbook hosted on GitHub (coreyhaines31/marketingskills). This serves as a documentation reference for advanced lead routing and does not involve the execution of remote code.

signup