tag-duplicate-prs-issues

Fail

Audited by Gen Agent Trust Hub on Apr 24, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill recommends installing software by piping remote shell scripts directly into the bash interpreter from an untrusted source (github.com/dutifuldev). This pattern allows the external source to execute arbitrary code on the user's system.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection through the ingestion of untrusted data from GitHub.
  • Ingestion points: Pull request and issue titles, bodies, and comments are fetched via ghr pr view and ghr search commands.
  • Boundary markers: There are no protective delimiters or instructions for the agent to ignore potentially malicious commands embedded in the retrieved content.
  • Capability inventory: The skill utilizes ghr, prtags, and uvx, which provide the agent with capabilities to read/write files and interact with the GitHub API.
  • Sanitization: No sanitization or validation is performed on the data retrieved from GitHub before it is processed by the agent.
  • [EXTERNAL_DOWNLOADS]: The skill fetches and executes the pr-search-cli tool using uvx without pinning a specific version or performing integrity checks.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/dutifuldev/prtags/main/scripts/install-prtags.sh, https://raw.githubusercontent.com/dutifuldev/ghreplica/main/scripts/install-ghr.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Apr 24, 2026, 04:51 AM