The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by design, as it instructs the agent to aggregate content from external and potentially untrusted communication channels.
Ingestion points: Files examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md direct the agent to retrieve data from Slack messages, emails, Google Drive documents, and external press articles.
Boundary markers: The instructions lack explicit delimiters or specific directives to ignore instructions embedded within the source material being summarized.
Capability inventory: The skill does not contain executable scripts or code; however, it relies on the agent's underlying capabilities to access and read organizational data sources.
Sanitization: There are no provided instructions for sanitizing, filtering, or escaping content retrieved from external sources before it is processed and formatted into the final output.
[NO_CODE]: The skill is composed exclusively of Markdown documentation and instruction files. It does not include any Python scripts, Node.js modules, or other executable binaries.

internal-comms