The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface as it is instructed to ingest and process data from external URLs (specifically docs.saleor.io) using the WebFetch tool.
Ingestion points: Documentation fetch commands in SKILL.md targeting Saleor developer guides.
Boundary markers: Absent; there are no specific instructions to the agent to ignore potentially malicious content embedded within the fetched documentation.
Capability inventory: The skill is allowed to use Bash, Write, Edit, and Read tools, which could be exploited if the fetched content contained instructions interpreted as commands.
Sanitization: No explicit sanitization or content validation steps are defined for the fetched external documentation.
[SAFE]: All external network requests and documentation references target docs.saleor.io, the official domain for the well-known Saleor e-commerce platform. These are considered trusted/well-known sources for the purpose of this skill. No evidence of obfuscation, hardcoded credentials, or unauthorized command execution was found.

saleor-orders