The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted external data which creates a surface for indirect prompt injection attacks.
Ingestion points: The skill ingests data from external sources including Git tags (e.g., v*.*.*), commit short hashes ({commit_short}), and the content of test outputs (such as API JSON responses) to generate reports and name artifacts.
Boundary markers: There is no evidence of boundary markers or specific instructions to the agent to ignore embedded instructions within the ingested data during report generation or command construction.
Capability inventory: The skill utilizes subprocess execution for various operations, including npm, npx, git, and aws CLI tools.
Sanitization: The instructions do not define sanitization or validation logic for external data before it is interpolated into prompts or report templates.
[COMMAND_EXECUTION]: The skill instructions and documentation examples include the execution of various shell commands to perform its primary functions.
Evidence: The skill documents the use of npm test, npx aiwg, git push, and aws s3 sync. These commands are standard for the tool's purpose of test automation and baseline synchronization with cloud services like Amazon S3.

regression-auto-baseline