Back to skill

Security audit

spec-driven-developm

Security checks for vulnerabilities and agentic risk

Overview

The skill does not show malicious behavior, but it asks for broad command, file, API, and credential-related authority that is not well scoped to writing specifications.

Review this skill carefully before installing. It appears to be a generic generated skill rather than a tightly scoped spec-writing assistant. Only use it in a constrained environment, avoid giving it real API keys unless you know exactly what service it will call, and require explicit approval before it runs commands or processes local files.

Vulnerability Patterns
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (6)

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill is presented as a specification-authoring tool, but its documented behavior is generic automation rather than constrained spec creation. This mismatch can cause an agent or user to invoke the skill under a low-risk assumption while actually enabling broader operational behavior than expected.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

High
Category
Not specified by scanner
Confidence
97% confidence
Finding

Declaring exec for a skill whose stated purpose is writing specifications introduces unnecessary command-execution capability. In an agent environment, this expands the attack surface substantially because prompt-driven or ambiguous instructions could cause local shell commands to run without clear justification tied to the skill's purpose.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

High
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill's description materially broadens from spec creation into automation, data analysis, workflow orchestration, API usage, file processing, and command execution. This overbroad scope is dangerous because it masks high-privilege behaviors behind an innocuous name, increasing the chance of unsafe invocation and privilege misuse.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The documentation instructs users to configure API keys and perform API/network interactions even though those capabilities are not clearly necessary for writing specs. Unjustified credential handling increases the risk of secret exposure, unintended outbound data transfer, and misuse of external services from a skill users may consider low risk.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The activation description is ambiguous and overly broad, including vague language around automation, data analysis, and workflow orchestration. Broad trigger conditions make accidental invocation more likely and can route users into a skill with stronger capabilities than they intended to use.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill references API keys, file handling, command execution, and API calls without prominent user-facing warnings about side effects, data exposure, or privilege implications. In an agent setting, insufficient disclosure can lead to users unknowingly authorizing sensitive operations such as outbound requests, filesystem access, or shell execution.

Content

No source excerpt is available for this finding.