One closed-loop iteration on an open PR — read CI checks + Claude / human review comments, triage against this repo's ADRs, apply valid suggestions, reply with reasoning on rejected ones, push fixes as Conventional Commits, and report status. Invoke as `/pr-iterate <PR#>`. Compose with `/loop /pr-iterate <PR#>` for continuous monitoring until green.
88%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
Critical
Do not install without reviewing
Detected a prompt injection in the skill instructions. The skill contains hidden or deceptive instructions that fall outside its stated purpose and attempt to override the agent’s safety guidelines or intended behavior.
The skill is a documented PR-iteration workflow with explicit guardrails (no force-push, no merge, human-only threads, escalation), but it auto-applies review fixes without the usual confirmation and resolves bot threads on the user's behalf, which is a modest, ambiguous form of acting beyond what the user might expect, so I rate it medium under the recall-first override.
The skill exposes the agent to untrusted, user-generated content from public third-party sources, creating a risk of indirect prompt injection. This includes browsing arbitrary URLs, reading social media posts or forum comments, and analyzing content from unknown websites.
The required snapshot step reads PR top-level comments and inline review-thread comments via `gh pr view` and `gh api .../pulls/$PR/comments`, and any GitHub user who can comment on the PR can place text there without the agent selecting a specific item, which is the medium GitHub PR reading category.
agranado2k/ai-report-platform
caeb0da
If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.