v1.0.0

stock_analysis_7step

BenignClawScan verdict for this skill. Analyzed May 1, 2026, 8:24 AM.

Analysis

This skill appears to be a disclosed remote Prana/Claw client for stock analysis, but users should notice that it sends prompts to a remote service and stores/uses an API key.

GuidanceBefore installing, understand that this is a remote-service wrapper rather than a fully local stock-analysis tool. Protect config/api_key.txt, do not commit it, verify the configured Prana/Claw base URL, and avoid sending private information beyond what is needed for the stock analysis.

Findings (3)

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.

Agentic Supply Chain Vulnerabilities

SeverityLowConfidenceHighStatusNote

package.json

"description": "Prana encapsulated skill — install deps for the Node runner: npm install", "dependencies": { "yaml": "^2.6.1" }

The optional Node runner requires installing an npm dependency with a floating semver range, which is normal for this runner but less reproducible than a pinned lockfile.

User impactIf you choose the Node runner, npm may install a newer compatible dependency version than the one originally tested.

RecommendationPrefer the Python runner if you want to avoid npm, or pin/review npm dependencies before using the Node runner.

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

SeverityMediumConfidenceHighStatusNote

README.md

脚本请求 `POST /api/claw/agent-run` ... 会在请求头加入 **`x-api-key: public_key:secret_key`** ... **自动落盘**：Python / Node 任一脚本在拉取成功后会默认写入 **`config/api_key.txt`**

The skill uses a Claw/Prana API credential and may persist it locally by default, so the credential file becomes sensitive account material.

User impactAnyone who can read the saved API-key file may be able to use the same service credential.

RecommendationProtect config/api_key.txt, avoid committing it, use the most limited key available, and set PRANA_SKILL_SKIP_WRITE_API_KEY=1 if you do not want the client to save fetched credentials.

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

SeverityLowConfidenceHighStatusNote

README.md

agent-run body：`skill_key`（= **脚本内嵌 `original_skill_key`**）、`question`（由 frontmatter 参数说明与用户消息组装）、`thread_id`、`request_id`。

The user's message is sent as a `question` to a remote Prana/Claw agent endpoint; this is expected for a remote encapsulated skill but is still a data boundary users should notice.

User impactYour stock-analysis request text is processed by the remote service rather than only on your machine.

RecommendationOnly include information you are comfortable sending to the configured Prana/Claw endpoint, and verify the base URL before use.