The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes data from external sources that may contain untrusted content, such as commit logs, diffs, and GitHub issue titles.
Ingestion points: scripts/commit-context.sh reads output from git log, git status, git diff, and gh issue list.
Boundary markers: Not explicitly defined for the gathered context data.
Capability inventory: The skill uses the Bash tool to execute git and gh commands and has the ability to create commits via git commit.
Sanitization: None detected; the agent processes raw output from the tools.
[COMMAND_EXECUTION]: The skill makes legitimate use of shell commands through the Bash tool to interact with the version control system and project issues.
Evidence: Execution of git, gh, and jq in scripts/commit-context.sh and various git commands in SKILL.md.
[DATA_EXPOSURE_EXFILTRATION]: The skill fetches issue data from GitHub using the official CLI tool.
Evidence: gh issue list is used in scripts/commit-context.sh to retrieve open issues for commit linking. This targets a well-known service and is consistent with the skill's purpose.

git-commit-workflow