Back to skill
v1.0.0

Quasi Coder

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 5:48 AM.

Analysis

This is an instruction-only coding helper whose behavior appears aligned with translating shorthand or natural-language requests into code, with no install, credential, network, or persistence requirements shown.

GuidanceThis skill appears safe to use as a prompt-only coding assistant. Because it is designed to reinterpret shorthand and improve flawed instructions, be explicit about constraints you do not want changed and review any code changes before applying them.

Findings (1)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

Abnormal behavior control

Checks for instructions or behavior that redirect the agent, misuse tools, execute unexpected code, cascade across systems, exploit user trust, or continue outside the intended task.

Agent Goal Hijack
SeverityInfoConfidenceHighStatusNote
SKILL.md
Always prioritize the **goal** over the **method** when the method is clearly suboptimal.

The skill intentionally tells the agent to favor its interpretation of the user's goal over a specified implementation method when it judges the method to be poor. This is coherent with the skill's coding-assistant purpose, but it is worth noticing because it can lead to non-literal implementations.

User impactThe agent may produce a different implementation approach than the user described if it believes that approach better satisfies the goal.
RecommendationReview generated code carefully and explicitly mark any required libraries, patterns, APIs, or implementation constraints as mandatory.