Skills
skills/steipete/agent-scripts/github-cache-hygiene/Gen Agent Trust Hub

github-cache-hygiene

Pass

Audited by Gen Agent Trust Hub on May 11, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill relies on the execution of various shell commands using the gh (GitHub CLI) and gitcrawl tools to manage issues, pull requests, and CI runs. It encourages the use of a local shim for caching purposes.
  • [PROMPT_INJECTION]: The skill is subject to potential indirect prompt injection because it instructs the agent to read and process content from GitHub issues and pull requests, which are attacker-controllable external sources.
  • Ingestion points: Untrusted data enters the agent context through commands like gh issue view, gh pr view, and gh pr diff in SKILL.md.
  • Boundary markers: No specific boundary markers or instructions to ignore embedded commands within the fetched data are present.
  • Capability inventory: The skill uses subprocess execution of the gh and gitcrawl command-line tools across the instructions in SKILL.md.
  • Sanitization: There is no mention of sanitizing, escaping, or validating the content retrieved from GitHub before processing it.
Audit Metadata
Risk Level
SAFE
Analyzed
May 11, 2026, 06:37 AM