skills/jeremylongshore/tons-of-skills-marketplace/providing-performance-optimization-advice/Gen Agent Trust Hub
providing-performance-optimization-advice
Pass
Audited by Gen Agent Trust Hub on Sep 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill analyzes external application codebase and infrastructure configurations, which constitutes an attack surface for indirect prompt injection if those files contain malicious instructions. * Ingestion points: Project codebase and infrastructure configuration files as specified in the SKILL.md prerequisites and instructions. * Boundary markers: There are no specific delimiters or protective instructions defined to separate analyzed data from the agent's core instructions. * Capability inventory: The skill is granted extensive capabilities including Read, Write, Edit, and Bash (SKILL.md), which could be leveraged if the agent follows malicious instructions from an external source. * Sanitization: No explicit content sanitization or validation mechanisms are described for the ingested project data.
Audit Metadata