The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill is designed to process data from workflow executions, which represents an attack surface for indirect prompt injection if the workflow triggers are controlled by untrusted external sources.
Ingestion points: The skill ingests data from the executions(action="debug") and executions(action="get-resolved-node-parameters") tools as described in SKILL.md.
Boundary markers: The skill does not explicitly define markers or delimiters to separate untrusted execution data from instructions.
Capability inventory: The skill has access to executions and workflows tools, which can be used to run or modify automated processes.
Sanitization: There is no evidence of sanitization or filtering applied to the execution results before the agent processes them.

debugging-executions