skills/finolabs/vibecode/fnl-update/Gen Agent Trust Hub

fnl-update

Pass

Audited by Gen Agent Trust Hub on Nov 4, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The script scripts/update_check.py utilizes subprocess.Popen to launch a detached background process. This is used exclusively for self-invocation of the script with a specific fetch flag, ensuring that network operations for version checking do not block the agent's main execution loop.\n- [EXTERNAL_DOWNLOADS]: The skill performs an automated check for new releases by connecting to the GitHub API. This operation is limited to fetching version metadata from the vendor's own repository on a well-known and recognized service.\n- [INDIRECT_PROMPT_INJECTION]: The skill ingests version strings from an external source, which represents a potential attack surface. To mitigate this, it implements the following security controls:\n
  • Ingestion points: Remote release data is fetched in scripts/update_check.py via the GitHub API.\n
  • Boundary markers: The skill instructions in SKILL.md enforce a specific output format for status updates and require explicit user consent for any subsequent installation command.\n
  • Capability inventory: The skill has the ability to make network requests and write local state files to a restricted directory.\n
  • Sanitization: A strict regex (v?[0-9]+\.[0-9]+\.[0-9]+) is applied to all incoming version tags, effectively preventing any malicious or non-numeric content from being processed or displayed to the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 4, 2026, 03:20 PM