Security audit

impact

Security checks for vulnerabilities and agentic risk

Overview

The skill provides coherent code-review guidance, and its local installation steps do not establish unauthorized background access.

The supplied skill instructions appear proportionate. Before building, review and pin the upstream source because its implementation was not available for verification. Analysis creates a local cache; keep proprietary code and credentials out of any results shared externally.

A.I.G

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

SkillSpector

Vulnerability Patterns

Rogue AgentSelf-Modification, Session Persistence
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 (1)

Session Persistence

Medium

Category: Rogue Agent
Confidence: 60% confidence
Finding: Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.
Content: Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.
git clone https://github.com/nano-harness/impact-analyzer.git cd impact-analyzer make build mkdir -p ~/.local/bin install -m 755 ./bin/impact ~/.local/bin/impact

text