The Agent Skills Directory

Indirect Prompt Injection (SAFE): The skill ingests untrusted data from GitHub issues and local knowledge files to identify similar past problems, which is a potential attack surface. * Ingestion points: Issue titles and descriptions retrieved via gh issue list and local project history in scripts/similar-issue-finder.sh. * Boundary markers: The templates do not currently implement explicit boundary delimiters or instructions to ignore embedded commands in external data. * Capability inventory: The skill is authorized to execute git and GitHub CLI commands and modify files to apply fixes. * Sanitization: The provided shell script scripts/similar-issue-finder.sh uses robust practices, including variable quoting and set -euo pipefail, to prevent shell-level command injection.

fix-issue