skills/shipshitdev/skills/bug/Gen Agent Trust Hub

bug

Pass

Audited by Gen Agent Trust Hub on Jul 20, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses 'gh' and 'git' commands to interact with GitHub repositories, which is necessary for its core functionality. These commands are defined within the 'allowed-tools' metadata.
  • [PROMPT_INJECTION]: The skill processes untrusted user data (bug descriptions and error traces) and incorporates them into a structured report and terminal commands.
  • Ingestion points: User input provided in the description for the bug report.
  • Boundary markers: No explicit delimiters are used to separate the user-provided data from the skill's internal instructions.
  • Capability inventory: The skill can execute 'gh issue create' and 'gh label create', which allows for the creation of persistent content on external platforms.
  • Sanitization: While the issue body is handled via a temporary file, the issue title is passed as a string argument to a shell command, which could be vulnerable to injection if the title contains shell meta-characters and the platform does not properly escape them.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 20, 2026, 01:29 PM
Security Audit — agent-trust-hub — bug