The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is instructed to ingest data from local environment files, which creates an attack surface for indirect prompt injection where malicious instructions in these files could influence agent behavior.
Ingestion points: The skill explicitly checks for and reads .agents/product-marketing.md, .claude/product-marketing.md, and product-marketing-context.md to establish context.
Boundary markers: The instructions do not define specific delimiters or guardrails to isolate the content of these files from the system instructions.
Capability inventory: The skill's primary capabilities involve text generation for marketing plans and outreach; no tools for file writing, network requests, or system command execution are utilized.
Sanitization: There is no evidence of sanitization or validation of the content read from the context files.
[EXTERNAL_DOWNLOADS]: The skill includes links to external informational documentation hosted on GitHub.
Evidence: The 'Tool Integrations' section in SKILL.md contains links to markdown files in the github.com/coreyhaines31/marketingskills repository for tools such as Crossbeam, Introw, and PartnerStack.

co-marketing