The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses WebSearch and WebFetch to retrieve documentation from official sites including docs.medusajs.com and typescriptlang.org. This is a standard and safe operation for documentation-oriented skills.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its pattern of processing external data alongside powerful tool capabilities.
Ingestion points: External content is ingested via WebSearch and WebFetch commands directed at Medusa and TypeScript documentation (SKILL.md).
Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external content as untrusted data or to ignore embedded instructions.
Capability inventory: The skill has access to sensitive tools including Bash, Write, and Edit, which could be exploited if malicious instructions were encountered in fetched content.
Sanitization: There is no evidence of sanitization or validation of the content retrieved from external sources before it is processed by the agent.

ts-modern