The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes user requests related to API integration, third-party services, and webhooks. This establishes an attack surface where an attacker could embed malicious instructions in external data (such as API responses or webhook payloads) which the agent might then process.
Ingestion points: Untrusted data enters the agent context through user queries involving batch handler patterns, third-party APIs, and integration workflows as described in SKILL.md.
Boundary markers: The skill lacks explicit boundary markers or delimiters to instruct the underlying model to ignore instructions embedded within the processed data.
Capability inventory: The skill is configured with broad permissions, including Bash(cmd:*), Write, and Edit, which could be exploited if an injection succeeds.
Sanitization: There are no instructions for the agent to sanitize or validate external content before using it in tool invocations or further processing.

batch-request-handler