The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process raw GitHub Actions workflow logs, which could potentially contain malicious instructions intended to manipulate the agent's behavior during analysis.
Ingestion points: The skill analyzes workflow logs provided as raw text or files as described in the "Log Ingestion & Redaction" section.
Boundary markers: The instructions do not specify the use of delimiters or specific markers to isolate the ingested log content from the agent's instructions.
Capability inventory: The skill empowers the agent to propose code modifications and generate diff outputs based on the analyzed data.
Sanitization: The skill places the responsibility for redaction on the user and does not implement automated sanitization or escaping logic for the agent when processing log content.

github-actions-debugger