Security audit

sngs-helper

Security checks for vulnerabilities and agentic risk

Overview

The skill provides local code search with clearly disclosed installation and saved indexes, without evidence of hidden background activity.

Review and preferably pin the upstream source revision before building; its executable code was outside the supplied artifact. Limit indexing to intended repositories and keep indexes and search output private. Set SNGS_NO_STATS=1 to disable the documented local statistics.

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 34)May include surrounding context.
git clone https://github.com/nano-harness/sparse-ngram-search.git cd sparse-ngram-search cargo build -p sngs --release mkdir -p ~/.local/bin install -m 755 ./target/release/sngs ~/.local/bin/sngs

text