bk-cli-monitor
Pass
Audited by Gen Agent Trust Hub on Nov 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill allows the agent to ingest data from external observability systems, creating a surface for indirect prompt injection.
- Ingestion points: Data is ingested via commands documented in SKILL.md, including
bk-cli monitor log search_logs,bk-cli monitor apm search_spans, andbk-cli monitor alert get_alert_info. - Boundary markers: There are no explicit delimiters or instructions provided to differentiate between the agent's core instructions and the potentially untrusted content of the retrieved logs or traces.
- Capability inventory: The agent is empowered to execute a suite of
bk-climonitoring and management commands. - Sanitization: The skill documentation does not define any methods for filtering or sanitizing the content fetched from the monitoring platforms.
Audit Metadata