skills/agentic-os-org/anolisa/github/Gen Agent Trust Hub

github

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPRIVILEGE_ESCALATIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches a repository configuration file from the official GitHub CLI domain (cli.github.com) to enable package installation.
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using the gh CLI and the dnf package manager for installation and repository interaction.
  • [PRIVILEGE_ESCALATION]: The installation process involves modifying system configuration files in /etc/yum.repos.d/ and mentions that sudo permissions may be required for package installation.
  • [INDIRECT_PROMPT_INJECTION]: The skill interacts with external repository data such as issue titles, PR descriptions, and CI logs. Malicious content within these GitHub resources could attempt to influence the agent's subsequent actions. Ingestion points: Data retrieved through gh pr, gh issue, gh run, and gh api commands as described in SKILL.md. Boundary markers: The instructions do not define specific delimiters or instructions to separate untrusted repository content from agent instructions. Capability inventory: The skill leverages the gh CLI, which provides the capability to read from and write to GitHub repositories. Sanitization: There is no mention of sanitizing or validating data fetched from the GitHub API before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 03:58 AM