The Agent Skills Directory

[NO_CODE]: The skill is composed strictly of Markdown documentation and instructional text. It does not contain any executable scripts, binaries, or command-line execution patterns.
[EXTERNAL_DOWNLOADS]: The NOTICE.md file references a public GitHub repository from Cosmic Stack Labs as the upstream source. This reference is for attribution and documentation purposes and targets a well-known service.
[PROMPT_INJECTION]: The skill processes untrusted user responses to generate summaries, identify patterns, and suggest action items, which creates a surface for indirect prompt injection.
Ingestion points: User-provided responses to standup, reflection, and retrospective prompts defined in SKILL.md.
Boundary markers: Absent. The skill lacks explicit delimiters for user content, although it instructs the agent to separate user observations from its own interpretations.
Capability inventory: The skill includes instructions to suggest action items (e.g., calendar adjustments) and offers optional data export to external files or services as described in the instructions.
Sanitization: Absent. There is no mention of sanitizing or escaping the user-provided data before processing.

daily-standup-journal