fivem
Pass
Audited by Gen Agent Trust Hub on Apr 26, 2026
Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection by ingesting and processing untrusted data.
- Ingestion points: User-uploaded FiveM resource files (config.lua, scripts), console error snippets, and GitHub search results (SKILL.md).
- Boundary markers: Absent. The skill lacks explicit delimiters or instructions for the agent to ignore potentially malicious commands embedded in these external sources.
- Capability inventory: The agent is instructed to perform file modifications, execute SSH key generation, and search GitHub repositories (SKILL.md).
- Sanitization: Absent. There is no mention of validating or sanitizing the content of resources retrieved from external sources like GitHub.
- [COMMAND_EXECUTION]: The skill directs the agent to perform SSH key generation (ed25519). This involves the execution of cryptographic commands and the handling of sensitive credentials (private keys) within the execution context, which could lead to exposure if not managed with high user oversight.
Audit Metadata