T09 · Insecure Skill Coding Practices
Error
- Location
scripts/scrape.py:19- Finding
Unrestricted URL Fetching Enables Server-Side Request Forgery
- Content
View full analysis
- Remediation
View remediation
Security audit
Nmb Scrapling
Security checks for vulnerabilities and agentic risk
Overview
The skill is a disclosed web-scraping helper, but it promotes anti-bot and Cloudflare bypass with broad arbitrary-URL fetching and limited safety scoping.
Install only if you intentionally need a powerful scraping tool and will use it on sites you are authorized to access. Run it in an isolated environment with restricted network egress, avoid using stealth or Cloudflare-bypass modes unless authorized, pin reviewed dependency versions, and treat scraped data as potentially sensitive.
Vulnerability Patterns
- Insecure DependenciesIntroduces malicious components through unsafe dependency sources
- Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
- Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
- Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
- Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
Findings (2)
T08 · Insecure Dependencies
Warning
- Location
SKILL.md:14- Finding
Unpinned Third-Party Dependency Installation
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (4)
Natural-Language Policy Violations
High
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The script explicitly advertises and exposes a
--stealthymode described as bypassing anti-bot protections, and imports aStealthyFetcherto do so. Even if framed as scraping convenience, functionality designed to evade access controls or bot-detection materially increases abuse potential and can facilitate unauthorized data collection against third-party sites.- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The trigger list includes broad natural-language phrases like 'extract data from' and generic scraping requests, which can cause the skill to activate in contexts where the user did not clearly intend to invoke a web-scraping and anti-bot-bypass capability. Because the skill supports Cloudflare bypass and large-scale crawling, accidental invocation increases the chance of unauthorized scraping, policy violations, or privacy-impacting behavior.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The description prominently advertises anti-bot bypass, Cloudflare circumvention, and large-scale scraping without any warning about legal, privacy, or system-integrity risks. In a skill that enables stealth fetching and bypass behavior, omission of safety guidance materially increases misuse risk by normalizing potentially abusive or unauthorized collection activities.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 86% confidence
- Finding
Most of the instructional content is presented only in Chinese, while the file does not state that the skill is region-specific or offer an English/locale choice. This can violate a language/locale policy when a skill imposes a language without opt-in or documented justification.
- Content
Static analysis
No suspicious patterns detected.