prp-loop
Run the autonomous cyclic PRP pipeline end to end (plan → implement → pr → review, looping review→fix until the PR is clean). Use when the user wants to "ship feature X end to end", "run the full PRP loop", "auto-implement and open a PR for a feature", or invokes $prp-loop.
80
100%
Does it follow best practices?
Run evals on this skill
Adds up to 20 points to the overall score
View guide
Critical
Do not install without reviewing
Security
1 critical severity finding. Installing this skill is not recommended: please review these findings carefully if you do intend to do so.
E006: Malicious code pattern detected in skill scripts.
What this means
Detected high-risk code patterns in the skill content — including its prompts, tool definitions, and resources — such as data exfiltration, backdoors, remote code execution, credential theft, system compromise, supply chain attacks, and obfuscation techniques.
Why it was flagged
This script intentionally invokes headless agent CLIs with flags that bypass permissions/sandboxing and automates git pushes/commits, creating a high-risk capability for data exfiltration, remote code execution, or repo tampering if abused.
Low
Low-risk findings.
1 low severity finding. Worth noting, but not necessarily harmful.
W011: Third-party content exposure detected (indirect prompt injection risk).
What this means
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.
Why it was flagged
Very likely: the orchestrator reads the PR review verdict and other stage “result” text from files/artifacts it produces, but at runtime those results ultimately come from the agent/skills interacting with the PR and its comments (review findings are outsider-authored code/PR discussion content, e.g., PR text/issues discussion), which are then injected back into the next fix prompts via `failures`/`pending_findings` and thus into the LLM context via `run_agent(prompt)`.
- Repository
- Wirasm/prp
- Commit
1142738
- Audited
- Security analysis
Is this your skill?
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.