simplify
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill interpolates the user-provided
$ARGUMENTSvariable directly into a prompt for thecdd-code-simplifiersub-agent. This creates a surface where instructions could be injected to override the sub-agent's behavior. - Ingestion point:
SKILL.mdvia$ARGUMENTS. - Boundary markers: Absent; user input is not delimited.
- Capability inventory: The sub-agent has file-modification capabilities.
- Sanitization: Absent.
- [COMMAND_EXECUTION] (SAFE): The skill suggests using
git diffandgit statusfor scope determination. These are standard read-only Git operations and do not pose a significant security risk.
Audit Metadata