The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill downloads and executes a shell script directly via curl ... | bash from https://aliyuncli.alicdn.com/setup.sh. This is a vendor-provided resource for the Alibaba Cloud CLI. While this pattern is generally high-risk, the domain is identified as a legitimate resource for the skill's author ('aliyun').
[COMMAND_EXECUTION]: The skill performs several command-line operations, including installing the aliyun-cli-emas-appmonitor plugin and configuring the CLI. The documentation in references/cli-installation-guide.md mentions using sudo to move binaries to system paths, which is a standard installation procedure.
[PROMPT_INJECTION]: The skill processes log data retrieved from mobile applications through the search-tlog API. This establishes an indirect prompt injection surface where external, potentially untrusted content from end-user devices is brought into the agent's execution context.
Ingestion points: Output from the aliyun emas-appmonitor search-tlog command as described in SKILL.md.
Boundary markers: None identified; log messages are not delimited or flagged to prevent the agent from interpreting embedded text as instructions.
Capability inventory: The skill has the capability to execute a variety of CLI commands and perform network operations via the Alibaba Cloud API.
Sanitization: There is no evidence of sanitization or filtering applied to the log messages before they are processed by the agent.

alibabacloud-emas-apm-remotelog