gs-show-me
Pass
Audited by Gen Agent Trust Hub on Nov 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute platform-specific commands to open generated visualization files.
- Evidence: In
SKILL.md, the instructions specify usingopen(macOS),xdg-open(Linux), andstart(Windows) to present generated HTML artifacts to the user. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the conversation to generate its output, creating a surface for indirect instructions to influence agent behavior.
- Ingestion points: The agent ingests the "current topic of conversation" (which may include user-provided code, pull request descriptions, or external files) as specified in
SKILL.md. - Boundary markers: The instructions do not specify strict delimiters or instructions to ignore embedded commands within the ingested content.
- Capability inventory: The skill has the ability to write local files (
show-me-{description}.html) and execute shell commands to open them. - Sanitization: There is no explicit requirement for the agent to sanitize or escape content before including it in the generated visualizations or using it in filenames.
Audit Metadata