The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external API contract definitions, which serves as an attack surface for indirect prompt injection where malicious instructions could be embedded in the data to influence the assessment.
Ingestion points: As described in SKILL.md, the skill ingests 'Old contract', 'New contract', and 'Known consumers' as its primary inputs.
Boundary markers: The skill does not specify the use of delimiters or specific instructions to the agent to disregard instructions embedded within the contract data.
Capability inventory: The skill metadata defines it as read-only and idempotent. The workflow is purely analytical (comparison and assessment) and does not involve subprocess calls, file writes, or network operations.
Sanitization: There is no mention of sanitization, validation, or escaping of the external contract content before it is processed by the agent.

compatibility-check