uxc-skill-creator

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands including bash, command -v, and rg (ripgrep) within its workflow and validation scripts. These commands are used for standard developer tasks such as environment verification, file searching, and running structural validation checks.\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection because it processes user-provided host and endpoint strings that are subsequently used in shell commands for endpoint probing.\n
  • Ingestion points: User-supplied host and endpoint parameters defined in the discovery workflow in SKILL.md.\n
  • Boundary markers: The skill does not implement specific boundary markers or 'ignore' instructions for the data ingested from user inputs.\n
  • Capability inventory: The skill allows for local command execution via uxc and script execution via bash using scripts/validate.sh.\n
  • Sanitization: While the workflow includes a step to normalize endpoint candidates, it does not include formal sanitization to prevent command injection from malicious host strings.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 03:14 AM