The Agent Skills Directory

Command Execution Pathway: The skill instructions permit the use of shell commands via the Bash tool to perform operations when specific platform tools are unavailable. This allows for flexible troubleshooting but involves the execution of local system commands.\n- Processing of External Content: The skill is designed to retrieve and analyze data from Power Automate flow definitions and execution logs. This creates a surface where the agent processes external content that could potentially contain instructions aimed at influencing the agent's behavior.\n
Ingestion points: Data is retrieved through tools such as get_run_actions and get_run_action_content (specified in SKILL.md).\n
Boundary markers: The skill does not explicitly use delimiters or instructions to treat the retrieved flow data as untrusted or separate from its internal logic.\n
Capability inventory: The agent has the capability to modify, delete, and run flows, as well as execute shell commands via the Bash tool.\n
Sanitization: No explicit sanitization or filtering steps are defined for the data retrieved during the diagnosis process.

debug-flow