fivem-deployment

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches build information and rolling EOL metadata from the official FiveM API at changelogs-live.fivem.net. This source is a standard service for the platform's artifact management.- [COMMAND_EXECUTION]: Instructions in rules/artifacts.md guide the agent to use curl to retrieve JSON payloads from official update servers, which is necessary for build verification.- [DYNAMIC_EXECUTION]: The skill uses a static python3 -c script to parse JSON data fetched from the network. This provides a focused utility for extracting specific support dates from the API response.- [INDIRECT_PROMPT_INJECTION]: The skill ingests data from external sources, creating a potential surface for injection if the remote API source were compromised.
  • Ingestion points: Data retrieved from the Cfx/FiveM changelog API in rules/artifacts.md.
  • Boundary markers: None; the agent is instructed to process the raw JSON output directly.
  • Capability inventory: curl and python3 command execution.
  • Sanitization: Absent; the process relies on standard JSON parsing to handle external content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 05:51 PM
Security Audit — agent-trust-hub — fivem-deployment