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
Bashtool to executepython3 -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, andWebSearchtools, 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