issue-creation

Pass

Audited by Gen Agent Trust Hub on May 9, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from users into GitHub issues which may be processed by other agents.
  • Ingestion points: Issue templates (Bug Report, Feature Request) in SKILL.md that accept user descriptions and logs.
  • Boundary markers: Absent; there are no instructions to the agent to treat the issue content as untrusted or to wrap it in delimiters.
  • Capability inventory: The skill uses gh issue create and gh issue edit to post content to an external repository.
  • Sanitization: Absent; input is directly placed into the command string without escaping or validation.
  • [COMMAND_EXECUTION]: The workflow involves executing shell commands with user-supplied arguments (title and body). If not handled with secure quoting by the executing agent, this could allow for command injection.
Audit Metadata
Risk Level
SAFE
Analyzed
May 9, 2026, 06:31 PM