The Agent Skills Directory

[COMMAND_EXECUTION]: Executes standard development commands including git log, git branch, and linear issue list. These commands are scoped to the local repository and the user's authenticated Linear environment, which is necessary for the skill's core purpose of status reporting.
[DATA_EXFILTRATION]: Reads project-specific metadata from .linear-project and .planning/STATE.md. No evidence of sensitive system file access (e.g., SSH keys, AWS credentials) or unauthorized data transmission to third-party domains. Network activity is limited to the official Linear CLI operations.
[PROMPT_INJECTION]: Ingests external data from git commit messages and Linear issue titles. While this presents an indirect prompt injection surface, the risk is mitigated by the skill's structured processing logic and its specific focus on report generation. The instructions do not attempt to bypass agent safety filters or override system prompts.

daily-standup