skills/phrazzld/claude-config/issue/Gen Agent Trust Hub

issue

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) as it processes untrusted content from GitHub issues.
  • Ingestion points: The skill fetches issue data (title, body, labels) using the gh issue view command in both /issue lint and /issue enrich subcommands.
  • Boundary markers: There are no explicit delimiters or 'ignore embedded instructions' warnings used when the agent processes or 'enriches' the fetched issue content.
  • Capability inventory: The skill has the capability to modify remote repository state via gh issue edit and can spawn sub-agents (Codebase explorer, Web researcher) to perform tasks based on the untrusted input.
  • Sanitization: No sanitization, escaping, or validation of the external issue content is performed before it is used to prompt sub-agents or used to rewrite the issue body.
  • [COMMAND_EXECUTION]: The skill executes system commands via the gh (GitHub) CLI tool. While these commands are central to the skill's functionality, they provide a mechanism for the agent to modify external state (GitHub issues) based on data that may contain malicious instructions.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 02:26 PM