The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The documentation (references/cli-installation-guide.md and references/cli-setup.md) references a script at https://aliyuncli.alicdn.com/setup.sh executed via curl | bash. This targets the official Alibaba Cloud CDN and is a standard distribution method for the vendor's CLI tool.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external Cloud APIs, which presents a surface for indirect prompt injection.\n
Ingestion points: Data enters the agent context through multiple aliyun CLI calls (e.g., describe-instance-ip-address, describe-ddos-event) as defined in SKILL.md.\n
Boundary markers: Absent. The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious data within the ingested JSON responses.\n
Capability inventory: The skill, as specified in SKILL.md, utilizes shell execution capabilities to run aliyun, grep, jq, wc, and date commands, and compiles these results into a report.\n
Sanitization: Absent. The skill extracts specific fields using jq and grep but does not perform explicit validation or sanitization of the values against a schema before including them in the markdown report output.

alibabacloud-ddos-security-monitor