The Agent Skills Directory

[PROMPT_INJECTION]: The skill is susceptible to Indirect Prompt Injection (Category 8) because it ingests and processes pull request review comments which are controlled by external users.
Ingestion points: Pull request review thread comments fetched via gh api graphql (SKILL.md, Step 1).
Boundary markers: Absent. The instructions do not define delimiters or provide warnings to ignore instructions embedded within the comments.
Capability inventory: The skill has the ability to modify local files (Edit, Write), execute shell commands (Bash), commit changes, and push code to remote repositories (SKILL.md, Step 3 and Step 5).
Sanitization: Absent. The skill does not implement filtering, escaping, or validation on the fetched comment bodies before they are used to guide the agent's actions.
[COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) and git to perform its primary tasks.
Executes gh api graphql to fetch and reply to review threads.
Executes git commit and git push to manage code changes.
Executes gh issue create to document follow-up work.
These commands are standard for the skill's purpose and use the local environment's authenticated identity.

forge-address-pr-feedback