The Agent Skills Directory

[SAFE]: The skill functions as a legitimate vendor resource authored by tencentcloudbase. All external console links and API interactions target official tcb.cloud.tencent.com infrastructure, which is consistent with the skill's diagnostic purpose.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an inherent surface for indirect prompt injection because its primary function involves the ingestion and interpretation of untrusted log data from external sources.
Ingestion points: Untrusted environment data enters the agent context via tool outputs from queryLogs, listFunctionLogs, and getFunctionLogDetail (SKILL.md).
Boundary markers: The instructions do not define specific delimiters or instructions to ignore embedded commands when the agent processes log content.
Capability inventory: The skill uses diagnostic tools such as queryEnv, queryFunctions, and queryCloudRun to gather resource status and metrics (SKILL.md).
Sanitization: The agent is instructed to search for specific structural patterns (e.g., 'ERROR', '429', 'TIMEOUT') rather than executing content found within logs, minimizing the risk associated with this surface.

ops-inspector