The Agent Skills Directory

[DATA_EXPOSURE]: The skill manages a service authentication token (STACKTREE_API_KEY). It instructs the agent to retrieve this from environment variables or prompt the user, which aligns with standard security practices for API-based tools.
[COMMAND_EXECUTION]: The skill relies on a local shell script (scripts/publish.sh) to transmit the generated HTML content to the service provider. This is a controlled execution of a skill-provided component.
[EXTERNAL_DOWNLOADS]: The skill interacts with the stacktr.ee domain for content publication and key management. While automated scanners flagged the API key management URL, this domain is the primary service provider for the skill's functionality.
[INDIRECT_PROMPT_INJECTION]: The skill acts as a data aggregator, which introduces a surface for indirect prompt injection from untrusted external sources.
Ingestion points: The skill processes content from external feeds, email inboxes, and internal metric summaries to build the daily brief.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for the agent when processing these external data sources.
Capability inventory: The skill has the capability to execute shell commands and perform network operations via the publish.sh script.
Sanitization: The skill documentation includes a recommendation to keep PII scanning enabled (block) to prevent the accidental publication of sensitive information found in ingested data.

stacktree-daily-brief