v1.2.0

Nano Triple

ReviewClawScan verdict for this skill. Analyzed May 1, 2026, 4:54 AM.

Analysis

The image-generation purpose is coherent, but the runtime instructions put the user's raw prompt into shell commands and depend on an undeclared external helper/API key, so it should be reviewed before use.

GuidanceBefore installing, verify the referenced `nano-banana-pro` helper and ensure prompts are passed safely without shell interpretation. Be aware that each use makes three Gemini image requests, may consume API quota, and may send your prompt text to the provider.

Findings (4)

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.

Tool Misuse and Exploitation

SeverityMediumConfidenceMediumStatusConcern

SKILL.md

Use the user's EXACT prompt... Don't modify it... uv run ~/.npm-global/lib/node_modules/clawdbot/skills/nano-banana-pro/scripts/generate_image.py --prompt "[USER'S EXACT PROMPT]"

The skill directs the agent to place user-controlled text into a bash command. Without explicit escaping or argv-safe execution, shell metacharacters in the prompt could be interpreted by the shell.

User impactA prompt containing shell syntax could cause unintended local command behavior when the agent follows the skill.

RecommendationPass the prompt through a safe tool/API argument interface or a reviewed wrapper, not by composing a shell command string; explicitly require proper escaping before execution.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

SKILL.md

uv run ~/.npm-global/lib/node_modules/clawdbot/skills/nano-banana-pro/scripts/generate_image.py

The core function depends on a helper script from another local skill/global npm path, while this package is instruction-only and provides no install spec or bundled helper code.

User impactThe actual image-generation behavior depends on local code not included in this artifact set.

RecommendationVerify the installed `nano-banana-pro` helper script and its source/version before using this skill.

Permission boundary

Checks whether tool use, credentials, dependencies, identity, account access, or inter-agent boundaries are broader than the stated purpose.

Identity and Privilege Abuse

SeverityLowConfidenceHighStatusNote

SKILL.md

Uses `GEMINI_API_KEY` from environment or openclaw config.

The skill uses a provider credential to generate images. This is expected for Gemini-backed image generation, but users should notice the credential and quota implications.

User impactUsing the skill may consume Gemini API quota or act under the user's configured Google/Gemini account.

RecommendationUse a limited-scope API key where possible and monitor quota or billing for repeated three-image generations.

Sensitive data protection

Checks for exposed credentials, poisoned memory or context, unclear communication boundaries, or sensitive data that could leave the user's control.

Insecure Inter-Agent Communication

SeverityLowConfidenceMediumStatusNote

SKILL.md

--prompt "[USER'S EXACT PROMPT]" ... Uses `GEMINI_API_KEY` from environment or openclaw config.

The user's prompt is intended to be passed to a Gemini-backed image-generation provider; the artifacts do not describe provider-side retention or privacy boundaries.

User impactAnything typed into the image prompt may be processed by the external image-generation service.

RecommendationAvoid putting secrets, private personal data, or confidential business information in image prompts unless the provider terms are acceptable.