The Agent Skills Directory

[PROMPT_INJECTION]: No evidence of prompt injection or instructions to bypass safety guidelines was found. The instructions are focused on hardware selection logic.
[DATA_EXPOSURE_AND_EXFILTRATION]: No hardcoded credentials or sensitive file paths were detected. The skill references local repository documentation and vendor data sheets for board specifications.
[OBFUSCATION]: No base64, hex-encoding, zero-width characters, or other obfuscation techniques were found.
[UNVERIFIABLE_DEPENDENCIES_AND_REMOTE_CODE_EXECUTION]: The skill does not perform any package installations or remote script executions. It is a logic-based skill for decision-making.
[INDIRECT_PROMPT_INJECTION]: The skill involves ingesting data from external sources such as vendor product pages and datasheets to verify hardware constraints. This represents a potential surface for indirect injection if those sources are compromised, though the skill's role is primarily analytical.
Ingestion points: External vendor product pages, MCU/module datasheets, and board schematics referenced in the 'Intake' section.
Boundary markers: None explicitly defined in the instructions for external data ingestion.
Capability inventory: The skill generates a decision record and compact table. No code execution, file writing, or network transmission capabilities are present in this skill.
Sanitization: No specific sanitization or validation logic for external content is described.
[DYNAMIC_EXECUTION]: No runtime compilation or dynamic code assembly was found.

board-selection