Skill flagged — suspicious patterns detected
ClawHub Security flagged this skill as suspicious. Review the scan results before using.
Phoenix Code Review
v1.2.0Reviews Phoenix code for controller patterns, context boundaries, routing, and plugs. Use when reviewing Phoenix apps, checking controllers, routers, or cont...
⭐ 0· 79·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
OpenClaw
Suspicious
medium confidencePurpose & Capability
Name and description match the actual contents: this is a Phoenix code-review checklist with examples for controllers, contexts, plugs, and routing. No unrelated binaries, installs, or credentials are requested.
Instruction Scope
The SKILL.md is purely guidance and stays within expected scope, except for one instruction: 'Load and follow [review-verification-protocol](../../../../skills/review-verification-protocol/SKILL.md) before reporting any issue.' That asks the agent to load a SKILL.md outside this package (a relative path reaching into ../../../../skills/...), which is a cross-skill file access not declared by the skill and could cause the agent to read other skills or traverse directories. While the referenced item could be a legitimate verification protocol, the instruction grants the agent implicit permission to access files outside the skill boundary and is an incoherence worth flagging.
Install Mechanism
No install spec and no code files that would be written or executed — instruction-only. This is the lowest-risk category for installs.
Credentials
No environment variables, credentials, or config paths are requested. The skill does not ask for secrets or unrelated service tokens.
Persistence & Privilege
Flags show always:false and the skill is user-invocable. It does not request permanent presence or system-wide configuration changes.
What to consider before installing
This skill appears to be a straightforward Phoenix code-review checklist and doesn't request credentials or install anything, which is good. The main concern is the line that tells the agent to 'load and follow' a SKILL.md located at a relative path that escapes the skill folder (../../../../skills/review-verification-protocol/SKILL.md). Before installing or enabling this skill, confirm what that referenced document contains and whether your agent is allowed to access other skills or filesystem paths. If you don't control the agent runtime, ask the platform how cross-skill file reads are handled. If you want to be cautious, only enable this skill in contexts where it must be run manually and avoid granting it autonomous invocation until you verify the external reference.Like a lobster shell, security has layers — review code before you run it.
latestvk9711hg2bz4ywg6aag2kdtfjss83d7k7
License
MIT-0
Free to use, modify, and redistribute. No attribution required.