show-me
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to use
Bash(open path/to/show-me-{description}.html)to display generated artifacts. Using a model-generated variable like{description}within a shell command creates a potential command injection vector if the input is not strictly validated or sanitized. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation data to create visual summaries, presenting an attack surface where malicious data could influence the generated content or behavior.
- Ingestion points: Conversation topics and user-provided data processed in
SKILL.mdto generate diagrams and HTML. - Boundary markers: Absent; the instructions do not specify delimiters to isolate untrusted data from the skill's logic.
- Capability inventory: The skill maintains the ability to write local file content and execute the
opencommand as part of its visual output process. - Sanitization: Absent; there are no instructions for sanitizing the input data or the generated
{description}string before it is used in a file path or shell execution.
Audit Metadata