Security audit

Security Sentinel Ultimate

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent local security-scanner skill, but its Markdown reports can be influenced by scanned files and its results may overstate scan completeness.

Install only if you treat this as a heuristic helper, not a definitive security gate. Run it only on directories you intentionally choose, and treat the Markdown report as untrusted evidence because scanned filenames or code strings may affect how the report appears.

A.I.G

Vulnerability Patterns

Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (3)

T01 · Skill Instruction Hijacking

Error

Location: scanner.py:468
Finding: Unescaped Attacker-Controlled Data in Agent-Facing Markdown Report
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scanner.py:181
Finding: Dangerous and Network Calls Can Bypass Detection Through Import Aliases
Content: View full analysis
= 2 and (chain[0], chain[1]) in DANGEROUS_CALLS: sev = ( "red" if chain[0] in RED_MODULES and chain[1] in RED_ATTRS else "yellow" ) self.dangerous_calls.append( ( self._line(node), f"{'.'.join(chain[:2])}({', '.join(self._arg_summary(node))})", sev, ) ) break if len(chain) >= 2 and (chain[0], chain[1]) in NETWORK_CALLS: self.network_calls.append( ( self._line(node), f"{'.'.join(chain[:2])}({', '.join(self._arg_summary(node))})", "yellow", ) ) break # Check for requests. style if len(chain) >= 2: pair = (chain[0], chain[1]) if pair in DANGEROUS_CALLS and not self.dangerous_calls: sev = ( "red" if chain[0] in RED_MODULES and chain[1] in RED_ATTRS else "yellow" ) self.dangerous_calls.append( (self._lin ...[truncated 2650 chars]
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: scanner.py:355
Finding: Unparseable Python Files Are Silently Reported as Clean
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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)

Ae1

High

Category: analysis-evasion
Confidence: 100% confidence
Finding: Referenced artifact was not completely inspected
Content: Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.
md
n_skill` tool accepts a `path` argument pointing to a skill directory. It runs `scanner.py` against all `.py` files in that directory tree and returns a Markdow

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 89% confidence
Finding: The skill exposes capabilities that can read files, access the network, and invoke a shell via python3 {{SKILL_DIR}}/scanner.py "{{path}}", but the manifest does not declare any scope restrictions such as permissions or allowed-tools. This weakens least-privilege controls and makes the skill harder to sandbox or review safely, especially because the provided path is user-controlled and the scanner is described as recursively analyzing directories.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dynamic_code_execution

Dynamic code execution detected.

Critical

Code: suspicious.dynamic_code_execution
Location: scanner.py:216