Back to skill

Security audit

Forge — Python Developer

Security checks for vulnerabilities and agentic risk

Overview

This is a plain Markdown skill for Python development help, with disclosed but broad coding and scraping capabilities and no hidden execution, persistence, or bundled code.

Install only if you want a broad Python development helper. For API and scraping work, provide only authorized targets and data, and require generated code to respect site terms, rate limits, privacy rules, and secret-handling best practices.

Vulnerability Patterns
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The description says 'Use when you need working Python code, API integrations, data processing, or CLI utilities,' which is a very broad activation cue for a manifest/markdown file. It does not define clear trigger boundaries, exclusions, or negative examples, increasing the risk of unintended invocation for general software requests.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill advertises web scraping output without any warning about privacy, authorization, rate limits, robots.txt, or terms-of-service constraints. In an autonomous coding context, this omission can normalize generation of scrapers that perform network activity against third-party sites in ways that create legal, privacy, or operational risk.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.