kimi-skills-finder

Pass

Audited by Gen Agent Trust Hub on Jun 19, 2026

Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes shell commands to list the contents of internal directories at /app/.agents/skills/ and /app/.user/skills/ to find matching capabilities.
  • [DATA_EXFILTRATION]: The skill performs network operations by visiting external domains including skillhub.cn via the browser_visit tool to find and document external skills.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from external web sources without implementing sanitization or boundary markers.
  • Ingestion points: External content retrieved from GitHub search results and the skillhub.cn website as defined in the Step 3 search workflow.
  • Boundary markers: Absent; the instructions do not include delimiters or specific warnings to the agent to ignore instructions embedded in the external content.
  • Capability inventory: The skill uses shell commands (listing and reading files) and has access to web browsing tools.
  • Sanitization: Absent; no filtering or validation logic is specified for the data retrieved from external repositories.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 19, 2026, 01:45 AM
Security Audit — agent-trust-hub — kimi-skills-finder