agent-lynx

Pass

Audited by Gen Agent Trust Hub on Nov 18, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill downloads and executes the agent-lynx CLI package from the NPM registry using npx --yes agent-lynx@latest or via global npm install. It also downloads a native TASM codec backend binary during the first execution of conversion tasks, which is verified using SHA-512.\n- [DYNAMIC_EXECUTION]: The skill employs a dynamic instruction-loading mechanism. It discovers and fetches task-specific sub-skills at runtime via the agent-lynx skills get command or by reading SKILL.md files and associated resources directly from the lynx-community/skills repository on GitHub.\n- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external developer artifacts, creating an ingestion surface for untrusted data.\n
  • Ingestion points: Performance traces, recorder replay JSON, recorder fixtures, and TASM templates.\n
  • Boundary markers: The instructions do not specify any delimiters or safety markers to isolate the content of these artifacts from the agent's instructions.\n
  • Capability inventory: The skill possesses the capability to execute shell commands (via the CLI tool) and read/write files on the local system.\n
  • Sanitization: No sanitization or validation of the data within the processed artifacts is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 18, 2026, 03:54 PM