Security audit

Dep Graph

Security checks for vulnerabilities and agentic risk

Overview

This skill is a small local dependency-manifest analyzer with no network, persistence, or credential behavior, though users should be aware it prints untrusted manifest text to the terminal.

Install only if you want a local helper for inspecting dependency manifests. Be careful running its terminal tree output on repositories you do not trust, because crafted dependency names or versions could visually manipulate terminal output; JSON output is safer for downstream processing but should still be treated as untrusted data.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (1)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/dep_graph.py:230
Finding: Unsanitized Manifest Data Permits Terminal Control-Sequence Injection
Content: View full analysis
Remediation: View remediation
= 0x20 and ord(ch) != 0x7F else f"\\x{ord(ch):02x}" for ch in text ) ``` Use it at the output boundary: ```python name = terminal_safe(dep.get("name", "")) version = terminal_safe(dep.get("version", "")) ver = f" @ {version}" if show_versions and version else "" lines.append(f"{prefix} {name}{ver}") ``` For stronger Unicode handling, also escape C1 controls (`U+0080`–`U+009F`) and consider replacing all characters whose Unicode category is `Cc`, except explicitly permitted formatting characters. ]]>

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
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

Findings (2)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 70% confidence
Finding: Without declared permissions the skill's intent is opaque and cannot be validated.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: Line L03 says to use the skill when asked to "list dependencies, show a dependency tree, check what packages a project uses, compare prod vs dev deps, or audit dependency counts." Several of these triggers are phrased broadly and there are no negative examples or scope constraints, which could cause the skill to activate for general package-related questions rather than only explicit project-manifest analysis tasks.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.