styling-expert
Pass
Audited by Gen Agent Trust Hub on May 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructions specify a mandatory memory protocol that uses the
Bashtool to executecat .claude/context/memory/learnings.md. This is a standard pattern for maintaining session context and persistence within the agent environment. - [SAFE]: The logic in
scripts/main.cjsand the execution hooks (pre-execute.cjs,post-execute.cjs) is benign and limited to descriptive help text and basic object validation. - [SAFE]: No indicators of data exfiltration, credential harvesting, obfuscation, or unauthorized network activity were found in the instructions or metadata.
- [SAFE]: While the skill analyzes external code (a surface for indirect prompt injection), this behavior is integral to its primary purpose as a styling reviewer and no malicious instruction manipulation was detected.
Audit Metadata