qa-to-issues

Pass

Audited by Gen Agent Trust Hub on Jun 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill invokes the gh issue create command to automate the creation of issues on GitHub based on the user's descriptions.
  • [PROMPT_INJECTION]: This skill is vulnerable to indirect prompt injection because it incorporates data from external files (the project codebase and UBIQUITOUS_LANGUAGE.md) into the prompts used to generate GitHub issues. This is a characteristic of the skill's intended functionality.
  • Ingestion points: Local files read during the background exploration phase (subagent_type=Explore) and specific configuration files like UBIQUITOUS_LANGUAGE.md.
  • Boundary markers: None identified. The skill does not use specific markers to separate codebase content from the agent's internal instructions.
  • Capability inventory: The skill has the capability to write to external systems via the gh tool.
  • Sanitization: There is no evidence of sanitization or validation of the content retrieved from the codebase before it is used to generate the final issue description.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 13, 2026, 07:09 AM
Security Audit — agent-trust-hub — qa-to-issues