The Agent Skills Directory

[NO_CODE]: The skill consists entirely of Markdown files and a license text. No executable scripts, binaries, or dependencies are included.\n- [SAFE]: No malicious patterns, prompt injections, or obfuscation were identified in the instructional content.\n- [SAFE]: The skill defines a vulnerability surface for indirect prompt injection by instructing the agent to ingest and summarize data from sources like Slack, Email, and Google Drive (as documented in examples/3p-updates.md, examples/company-newsletter.md, and examples/faq-answers.md). However, it contains no code to perform these actions and no instructions to execute arbitrary commands based on the content. Ingestion points: Slack messages, emails, Google Drive docs, and calendar events. Boundary markers: Absent. Capability inventory: No code provided. Sanitization: Absent.

internal-comms