Skills
skills/steipete/openclaw/tag-duplicate-prs-issues/Gen Agent Trust Hub

tag-duplicate-prs-issues

Fail

Audited by Gen Agent Trust Hub on Jul 13, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill instructs the agent to install the prtags utility by executing a remote shell script (https://raw.githubusercontent.com/dutifuldev/prtags/main/scripts/install-prtags.sh) piped directly into bash. This pattern executes unverified code from an external source with the user's shell privileges, posing a significant security risk.
  • [PROMPT_INJECTION]: The skill has a substantial attack surface for indirect prompt injection as it ingests untrusted data from GitHub pull requests and issues and uses it to perform grouping and annotation actions.
  • Ingestion points: Data is fetched from external sources using gh pr view, gh issue view, and gitcrawl commands.
  • Boundary markers: The instructions lack delimiters or warnings to ignore instructions embedded within the fetched content.
  • Capability inventory: The skill can execute local shell commands and perform authenticated writes to the prtags backend.
  • Sanitization: There is no mention of sanitizing or validating the external content before processing.
  • [COMMAND_EXECUTION]: The skill directs the agent to perform multiple shell commands, including tool installation and authentication (prtags auth login), which involves managing maintainer-level credentials and potentially interactive shell states.
Recommendations
  • HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/dutifuldev/prtags/main/scripts/install-prtags.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Jul 13, 2026, 02:11 PM
Security Audit — agent-trust-hub — tag-duplicate-prs-issues