cache-optimizer

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (HIGH): The skill analyzes external content (React components) and possesses high-privilege capabilities (Write, Edit), creating a significant attack surface.
  • Ingestion points: Processes untrusted local code through the Read, Grep, and Glob tools as defined in the skill's trigger conditions.
  • Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to ignore embedded instructions within the data being analyzed.
  • Capability inventory: The skill is granted Write and Edit permissions, which could be exploited to perform unauthorized file system modifications if the agent follows malicious instructions hidden in code comments or strings.
  • Sanitization: No sanitization or validation logic is defined to mitigate the risk of processing malicious inputs.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 08:06 AM