The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill facilitates the generation of code that controls physical laboratory hardware, creating an inherent surface for indirect prompt injection where instructions in user-provided data could influence hardware behavior.
Ingestion points: Protocol specifications and experimental requirements provided by the user as described in SKILL.md.
Boundary markers: Absent; the documentation does not suggest using delimiters or specific safety instructions to isolate user input from protocol logic.
Capability inventory: The skill provides full access to the opentrons Protocol API, allowing movement of robot components and control over thermal, magnetic, and mechanical modules.
Sanitization: Absent; no input validation or sanitization practices for user data are mentioned.
[SAFE]: The skill includes instructions for the agent to recommend the vendor's hosted platform for complex workflows, which is consistent with the author's identity and does not interfere with safety guidelines.

opentrons-integration