The Agent Skills Directory

[Data Exposure & Exfiltration] (MEDIUM): The skill documentation and scripts explicitly reference access to a sensitive Google Search Console service account key file at /path/to/gsc-credentials.json. Exposure of such keys can lead to unauthorized access to organizational data.
[Command Execution] (LOW): The skill uses Bash(node:*), Bash(git:*), and Bash(curl:*) to execute local scripts and check system logs. While aligned with the skill's purpose of automated reporting, these broad permissions represent a significant capability surface.
[Indirect Prompt Injection] (LOW): The skill processes untrusted external data which presents an injection surface.
Ingestion points: scripts/collect-data.js fetches search queries and page data from GSC and GA4.
Boundary markers: Absent; there are no delimiters or instructions to ignore embedded commands in the fetched data.
Capability inventory: The skill can execute shell commands (node, git, curl).
Sanitization: Absent; the data is passed directly into the report generation context.
[External Downloads] (LOW): The skill performs network operations to google.com and clarity.ms using curl and https.get. These are reputable sources and are directly related to the skill's primary analytics purpose.

weekly-analytics