The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill establishes a process for agents to explore and document findings from external software. This creates a surface where the agent could ingest untrusted data (e.g., from UI fields or logs) that might contain malicious instructions. \n- Ingestion points: Capturing observations and findings during software exploration in SKILL.md. \n- Boundary markers: The documentation templates do not provide specific markers to isolate external data from the agent's instructions. \n- Capability inventory: The skill uses orchestration tools like Task and FleetManager and memory storage in the aqe/exploratory/ namespace. \n- Sanitization: There are no explicit instructions for sanitizing or validating external content before it is recorded.

exploratory-testing-advanced