agent-creator
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill processes user-supplied input via the
$ARGUMENTSplaceholder inSKILL.md, creating a surface for indirect prompt injection.\n - Ingestion points: User input through
$ARGUMENTSat the beginning ofSKILL.md.\n - Boundary markers: None present; the input is interpolated directly without delimiters or 'ignore' instructions.\n
- Capability inventory: The skill defines access to tools including
Bash,Write, andEditvia frontmatter configuration.\n - Sanitization: No sanitization or validation of the input is performed before interpolation.
Audit Metadata