skills/deevus/tea-skills/create-issue/Gen Agent Trust Hub

create-issue

Pass

Audited by Gen Agent Trust Hub on Jun 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the tea CLI tool to interact with Gitea or Forgejo servers for issue management.
  • [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface where untrusted data is interpolated into command-line arguments.
  • Ingestion points: The skill accepts user-provided input for the issue title, description, labels, and assignees, which are then used as flags for the tea issues create command.
  • Boundary markers: There are no explicit boundary markers or delimiters used to wrap the user-provided strings to differentiate them from instructions.
  • Capability inventory: The skill's primary capability is the execution of shell commands through the tea utility.
  • Sanitization: No sanitization, validation, or escaping of the user-supplied content is specified before the data is passed to the shell environment.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 20, 2026, 09:18 AM
Security Audit — agent-trust-hub — create-issue