setup
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFEPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface by interpolating unsanitized user arguments directly into the instruction context via the 'Task: {{ARGUMENTS}}' line. This could allow a user to override agent behavior by providing malicious instructions as arguments. * Ingestion points: The {{ARGUMENTS}} placeholder in SKILL.md. * Boundary markers: None; the input is not enclosed in delimiters or accompanied by instructions to ignore embedded commands. * Capability inventory: The skill routes to sub-skills (omc-setup, mcp-setup) responsible for installation and environment configuration. * Sanitization: No validation or filtering of user input is performed.
- [NO_CODE]: The skill contains only documentation and routing logic in markdown format; no Python, JavaScript, or shell scripts were detected.
Audit Metadata