prism-component

Pass

Audited by Gen Agent Trust Hub on Jul 1, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to execute python3 -m prism_agent.uiux search (SKILL.md, Design Intelligence section). The command uses shell interpolation for variables like {detected_framework}, which are populated by scanning the project's local environment. This could allow for argument injection if project files (e.g., package.json) contain malicious metadata.
  • [PROMPT_INJECTION]: The skill processes untrusted data from the local project, creating a surface for indirect prompt injection.
  • Ingestion points: The agent reads project-level files including package.json, tsconfig.json, and existing component source code to determine the stack and patterns.
  • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat the content of these files as untrusted or to ignore embedded instructions.
  • Capability inventory: The agent is authorized to use Write, Edit, Bash, WebFetch, and WebSearch tools, which could be misused if the agent's logic is subverted by malicious file content.
  • Sanitization: There is no evidence of sanitization or validation of the input gathered from the project environment before it is used in code generation or command execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 1, 2026, 02:48 PM
Security Audit — agent-trust-hub — prism-component