The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection because it instructs the agent to retrieve external data via the WebFetch tool to guide implementation.
Ingestion points: External documentation URLs targeting developer.salesforce.com within SKILL.md.
Boundary markers: The instructions do not specify boundary markers or delimiters to help the agent distinguish between documentation content and potential instructions embedded within that content.
Capability inventory: The skill is granted Write, Edit, and Bash permissions in its allowed-tools, providing a functional path for potentially malicious instructions ingested from external documentation to affect the system.
Sanitization: The skill does not provide specific instructions for sanitizing or validating the content retrieved from external sources before the agent processes it.

sf-integrations