The Agent Skills Directory

Prompt Injection (LOW): The skill is susceptible to indirect prompt injection attacks because it directs the agent to ingest and summarize information from untrusted sources.
Ingestion points: File instructions in '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 Calendar events.
Boundary markers: There are no instructions or delimiters provided to help the agent distinguish between its system instructions and potentially malicious commands embedded within the retrieved documents or messages.
Capability inventory: The agent utilizes read access to sensitive organizational data and possesses the capability to output summaries to company-wide channels.
Sanitization: The skill lacks requirements for the agent to sanitize, escape, or validate the content it retrieves before incorporating it into communications.
No Code (SAFE): The skill consists entirely of Markdown instruction files and does not include executable scripts or external package dependencies.

internal-comms