whatis
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute the shell command
opento display the generated HTML file to the user. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to "gather enough context" from external sources to explain a topic, which creates a surface where malicious instructions in external content could potentially influence the agent's output or activities.
- Ingestion points: The agent is directed to gather context from the current environment or external sources to inform the diagram creation (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the gathered context are provided.
- Capability inventory: The skill possesses the ability to write files to temporary directories (
/tmp,$TMPDIR) and execute shell commands (open). - Sanitization: The instructions do not include specific steps to sanitize or escape data retrieved from external sources before incorporating it into the generated HTML/SVG code.
- [DYNAMIC_EXECUTION]: The skill dynamically generates HTML and SVG code at runtime based on user requests and gathered context, which is then written to the local filesystem and opened using a system utility.
Audit Metadata