kimi-cli-help

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest data from external sources to answer user questions, which creates a potential surface for indirect prompt injection if the external content is compromised.
  • Ingestion points: Fetches documentation index and specific pages from https://moonshotai.github.io/kimi-cli/.
  • Boundary markers: None explicitly defined in the skill instructions.
  • Capability inventory: Includes reading local files and cloning the moonshotai/kimi-cli repository (following user confirmation).
  • Sanitization: No specific sanitization or filtering of the ingested documentation content is described.
  • [EXTERNAL_DOWNLOADS]: The skill references and fetches content from external vendor-owned resources.
  • Evidence: Accesses documentation at https://moonshotai.github.io/kimi-cli/ and mentions cloning the source code repository at https://github.com/MoonshotAI/kimi-cli for exploration.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 05:13 AM
Security Audit — agent-trust-hub — kimi-cli-help