show-me
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted conversation topics to generate visual content and corresponding filenames. An attacker could attempt to embed instructions within the conversation to manipulate the agent's behavior during the visualization process.
- Ingestion points: The current topic of conversation (processed by instructions in SKILL.md).
- Boundary markers: None present to delimit user input from instructions.
- Capability inventory: The skill can write files and execute shell commands (
open). - Sanitization: No explicit instructions are provided to sanitize the
{description}variable before it is interpolated into a shell command. - [COMMAND_EXECUTION]: The skill uses the
Bash(open ...)command to display generated HTML files to the user. The use of a template variable{description}within this shell command, derived from the conversation topic, represents a potential command injection surface if the agent is coerced into using malicious characters in the filename.
Audit Metadata