The Agent Skills Directory

[SAFE]: The skill consists entirely of markdown documentation, templates, and guidance. It does not contain scripts, binaries, or command-line instructions.
[DATA_EXPOSURE]: The skill is configured to read from startup-context, which includes sensitive business information such as MRR, burn rate, and board composition. This access is explicitly declared in the frontmatter and is necessary for the skill's primary function of generating business reports.
[INDIRECT_PROMPT_INJECTION]: The skill presents a surface for indirect prompt injection as it processes external data into its output.
Ingestion points: Data is ingested from the startup-context resource and direct user input.
Boundary markers: The prompt lacks specific delimiters or "ignore instructions" warnings for the ingested context.
Capability inventory: The skill is limited to generating markdown text for display to the user. It has no capabilities for file system modification, network communication, or shell command execution.
Sanitization: There is no evidence of sanitization or filtering of the input data before it is interpolated into the report templates.

board-update