skills/vincentkoc/dotskills/crawlkit/Gen Agent Trust Hub

crawlkit

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill verifies releases and module information from the author's own repository (github.com/vincentkoc/crawlkit) through official Go proxy services.
  • [COMMAND_EXECUTION]: Utilizes system tools such as go and git to manage dependencies, run tests, and check binary versions.
  • [INDIRECT_PROMPT_INJECTION]: The process of reading code and tool output creates an ingestion surface for potentially untrusted data.
  • Ingestion points: Repo-local files (README.md, CONTRIBUTING.md) and CLI tool output (metadata --json).
  • Boundary markers: None present.
  • Capability inventory: Execution of Go tests and local CLI commands.
  • Sanitization: No explicit sanitization or filtering is applied to ingested data.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 10:52 AM