Back to skill

Security audit

Codebase Survey

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Markdown-only codebase survey workflow with some privacy-sensitive reporting guidance that users should narrow if they do not want velocity or operating-context analysis.

Install only if you are comfortable with an agent reading repository structure, recent git history, documentation, schema, and representative source files to produce a synthesized project report. If velocity, timeline, customer, or operating-style analysis is sensitive, tell the agent to omit maturity/velocity and future-reader context sections before running the skill.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This section directs the agent to infer team velocity, project build timeline, and user-specific operating context from the repository. That goes beyond codebase understanding into profiling people and organizational capability, which can expose sensitive operational metadata and create unnecessary collection/inference about individuals or teams.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The manifest frames this skill as surveying a codebase's structure, scope, architecture, and current state. While some state awareness is reasonable, explicit inspection of git branch topology and recent commit history adds repository forensics/velocity analysis capability that is not directly required to understand the codebase itself.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.