auto-review-loop
Autonomous multi-round research review loop. Repeatedly reviews using Gemini via gemini-review MCP, implements fixes, and re-reviews until positive assessment or max rounds reached. Use when user says "auto review loop", "review until it passes", or wants autonomous iterative improvement.
68
82%
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
3 findings: 1 critical severity, 1 high 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 document instructs autonomous, non-interactive exfiltration of full project context to an external reviewer, silent file writes, and remote command deployment/monitoring using the user's credentials (including reading local notification creds), which together enable unauthorized data exposure and remote actions without consent.
W007: Insecure credential handling detected in skill instructions.
What this means
The skill handles credentials insecurely by requiring the agent to include secret values verbatim in its generated output. This exposes credentials in the agent’s context and conversation history, creating a risk of data exfiltration.
Why it was flagged
The skill sends full project context to an external reviewer and explicitly requires saving and later pasting the reviewer's RAW response verbatim into output files, so any secrets present in the context or echoed back by the reviewer would be recorded and exposed—this forces the agent to handle/output potentially sensitive values verbatim.
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 instructs the agent to run remote commands and deploy services via SSH, start network/MCP services with the user's credentials, and to write/overwrite files silently without asking permission — actions that modify the machine's state and can compromise the host if misused.
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 workflow forwards full raw context and then saves and parses the external reviewer’s returned free-text response via the `mcp__gemini-review` MCP bridge (`review_start/review_reply_start` → `review_status.response`), which is outsider-authored text at runtime.
- Commit
f4f20f9
- 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.