diagram
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes the 'snip' CLI tool through the system shell to render visualizations. This is a core part of the skill's functionality and uses controlled input redirection from files in a specific temporary directory (~/.snip/tmp/).- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted conversation context to generate code for diagrams or HTML, which can be a vector for malicious instructions embedded in the source data.
- Ingestion points: User-provided conversation context is analyzed in Step 1 to generate visual content.
- Boundary markers: No specific delimiters are used to separate the instructions for the agent from the data being processed.
- Capability inventory: The skill utilizes file writing via the 'Write' tool and shell command execution via the 'snip' command.
- Sanitization: The skill's documentation explicitly states that HTML content is sandboxed and that '' and '' execution is disabled.
Audit Metadata