upload-element-previews

Pass

Audited by Gen Agent Trust Hub on Aug 21, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute the script upload-element-preview located within the project's packages/docs directory using the bun runtime. This is a standard automation task for repository maintainers but involves the direct execution of shell commands.\n- [INDIRECT_PROMPT_INJECTION]: The skill facilitates a potential command injection by interpolating an unvalidated user-supplied 'slug' directly into a shell command string (--element=<category>/<slug>).\n
  • Ingestion points: The agent is instructed to obtain the 'Element slug' from the user in Step 1.\n
  • Boundary markers: There are no instructions to use delimiters or ignore embedded instructions within the input.\n
  • Capability inventory: The agent has the capability to execute shell commands in the documentation package directory.\n
  • Sanitization: There are no instructions to sanitize, escape, or validate the user input before it is passed to the command line.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 21, 2026, 03:42 PM
Security Audit — agent-trust-hub — upload-element-previews