The Agent Skills Directory

[COMMAND_EXECUTION]: The skill interpolates the user-provided $ARGUMENTS directly into shell commands within SKILL.md. Examples include gh issue view "$ARGUMENTS" and git worktree add "worktree/issue-$ARGUMENTS". If the input is not strictly validated, an attacker could supply malicious shell metacharacters to execute unauthorized commands in the agent's environment.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from GitHub issues and PR comments, which can be authored by any GitHub user. This data is processed by an agent with broad system capabilities including shell access and file modification. \n * Ingestion points: GitHub issue content via gh issue view and PR comments via gh api. \n * Boundary markers: None identified; the skill does not instruct the agent to ignore or delimit instructions found within the issue or comment bodies. \n * Capability inventory: The skill uses Bash, Write, Edit, Glob, and Grep tools, allowing for extensive system interaction. \n * Sanitization: No sanitization or filtering of the fetched content is performed before processing.

issue-to-pr-resolver