slfg
Pass
Audited by Gen Agent Trust Hub on Apr 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface area.
- Ingestion points: Untrusted user data enters the context via the $ARGUMENTS variable in SKILL.md and is passed to the planning tool.
- Boundary markers: The skill lacks delimiters (such as XML tags or explicit block markers) around interpolated user input to distinguish it from instructions.
- Capability inventory: The workflow invokes powerful capabilities including code generation and modification (/ce:work, /ce:review) and automated browser testing (/systematic:test-browser).
- Sanitization: There is no evidence of input sanitization, filtering, or validation before the data is processed by subsequent tools.
Audit Metadata