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.
79
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
2 findings: 1 critical severity, 1 medium severity. 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
The script intentionally enables autonomous, unsandboxed agent actions (dangerous CLI flags, running external agent prompts that can see repo files), can commit/push changes and run arbitrary shell validation, creating high risk for data exfiltration, remote code execution, and supply-chain abuse if misused.
W013: Attempt to modify system services in skill instructions.
What this means
The skill prompts the agent to compromise the security or integrity of the user’s machine by modifying system-level services or configurations, such as obtaining elevated privileges, altering startup scripts, or changing system-wide settings.
Why it was flagged
The skill autonomously "executes the plan" (modifying the repo/state) and explicitly exposes a --dangerously-skip-permissions mode that bypasses permission safeguards, which can enable unmediated state-changing actions on the host.
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
The required workflow runs headless `claude -p "<prompt>"` and the prompt text includes `state['pending_findings']` (review verdict “blocking” strings) which come from the outsider-authored PR review content/feedback produced by the `prp-review` skill run over an existing PR by other contributors; that free-form text is then injected back into subsequent LLM prompts via the `stage_fix -> findings -> initial` path.
- 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.