Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > 📎 **Code example 1** (typescript) — see [references/examples.md](references/examples.md)
Security audit
requirements-analyst
Security checks for vulnerabilities and agentic risk
Overview
This is a requirements-analysis helper with documentation templates and illustrative code, and I found no hidden execution, credential use, persistence, or destructive behavior.
Install this if you want an agent to help draft and organize requirements artifacts. Review generated implementation tasks and test cases as planning suggestions, since they may go beyond strict requirements wording, but the package itself shows no security-sensitive behavior.
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 (5)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > 📎 **Code example 1** (typescript) — see [references/examples.md](references/examples.md)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md > 📎 **Code example 1** (typescript) — see [references/examples.md](references/examples.md)
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The manifest describes a requirements analyst focused on elicitation, user stories, stakeholder analysis, validation, and acceptance criteria. In contrast, this code generates implementation work items such as UI development, API endpoint creation, database schema updates, testing, and documentation tasks, which moves into project planning and solution implementation decomposition rather than requirements engineering itself.
- Content
Context-Inappropriate Capability
Medium
- Category
- Not specified by scanner
- Confidence
- 87% confidence
- Finding
While acceptance criteria definition is in scope, this method goes further by creating executable-style functional, edge-case, performance, and security test cases. Detailed test planning—especially specialized security and performance test generation—is not clearly justified by the manifest's narrower requirements-analysis purpose.
- Content
Static analysis
No suspicious patterns detected.