The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The script scripts/list_openapi_meta_apis.py fetches OpenAPI metadata and API specifications from api.aliyun.com. This is the official domain for Alibaba Cloud services and is recognized as a well-known service source.
[COMMAND_EXECUTION]: The skill uses shell commands to execute its metadata discovery script and to perform validation via py_compile. These operations are limited to the skill's local files and are part of the intended management workflow.
[INDIRECT_PROMPT_INJECTION]: The skill ingests external JSON metadata, creating a theoretical attack surface for indirect prompt injection if the metadata source were compromised.
Ingestion points: The scripts/list_openapi_meta_apis.py script downloads data from https://api.aliyun.com.
Boundary markers: No specific boundary markers or 'ignore' instructions are applied to the ingested metadata before it is presented to the agent.
Capability inventory: The agent can write discovery artifacts to the local filesystem and is instructed by SKILL.md to call Cloud APIs based on the discovered metadata.
Sanitization: The script performs standard JSON parsing to extract API names but does not include explicit content filtering for malicious instructions.
Risk assessment: The risk is considered safe because the data originates from a highly trusted, official vendor service.

aliyun-ccai-manage