github-actions-version-fix

Pass

Audited by Gen Agent Trust Hub on Jun 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides an 'Automated Check Script' and instructions for using the GitHub CLI (gh api) and standard utilities (grep, sed, cut) to retrieve and verify repository metadata. The script contains a shell injection vulnerability because it uses unquoted variables (e.g., $VERSION) when constructing CLI commands, which could allow execution of arbitrary code if the processed workflow file contains malicious strings.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection by ingesting and acting upon untrusted data from GitHub Actions workflow files.\n
  • Ingestion points: Workflow files read in SKILL.md via grep and sed.\n
  • Boundary markers: Absent.\n
  • Capability inventory: Subprocess execution via Bash tool and file system modification.\n
  • Sanitization: Absent; the script fails to sanitize or properly quote extracted data before using it in shell commands.\n- [EXTERNAL_DOWNLOADS]: The skill makes network requests to the official GitHub API using the gh command-line tool to fetch repository tags and releases.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 17, 2026, 08:17 AM
Security Audit — agent-trust-hub — github-actions-version-fix