The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process external data sources such as CRM notes and call transcripts to perform win-loss analysis and objection handling. If these sources contain maliciously crafted text or hidden instructions, they could attempt to influence the agent's output or behavior during the analysis process.
Ingestion points: The agent is directed to read and 'code' CRM notes and call transcripts (referenced in SKILL.md and references/win-loss-analysis.md).
Boundary markers: The instructions lack explicit boundary markers or warnings for the agent to disregard instructions embedded within the processed transcripts or notes.
Capability inventory: The skill's primary function is generating text-based sales collateral (markdown, outlines). It does not have capabilities for system command execution or network operations using the ingested data.
Sanitization: There is no mention of sanitizing or escaping content from external transcripts before processing.
[EXTERNAL_DOWNLOADS]: The skill includes references to an external GitHub repository (github.com/coreyhaines31/marketingskills) for a tools registry and integration guides. While these are currently presented as documentation links, they point to a third-party repository that is not part of the trusted vendor list.
Evidence: Links to https://github.com/coreyhaines31/marketingskills/blob/main/tools/REGISTRY.md and related integration files.

sales-enablement