Security audit

string-utils

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward string utility skill with some input-validation bugs, but no hidden access, persistence, network behavior, or deceptive instructions.

Reasonable to install for local string formatting helpers, but avoid exposing its chunk or custom-trim functions directly to untrusted user input unless you add validation and error handling. Treat HTML escaping as a convenience helper, not a complete security sanitizer for complex web contexts.

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 (2)

T09 · Insecure Skill Coding Practices

Error

Location: index.js:292
Finding: Unvalidated chunk size causes an infinite loop and memory exhaustion
Content: View full analysis
Remediation: View remediation

T09 · Insecure Skill Coding Practices

Warning

Location: index.js:98
Finding: Unescaped input in dynamic regular expressions permits regex manipulation and exceptions
Content: View full analysis
Remediation: View remediation
start && removable.has(str[end - 1])) end--; return str.slice(start, end); } ``` Apply equivalent logic to `trimLeft` and `trimRight`. If dynamic regular expressions must be retained: - Escape all character-class metacharacters, including `\`, `]`, `-`, and `^`, before interpolation. - Do not rely solely on the existing `escapeRegex` helper because escaping requirements inside a character class differ from general regex escaping. - Place construction in controlled error handling so malformed input cannot terminate a request or worker. - Limit the accepted length of `chars`. - Add tests covering backslashes, brackets, hyphens, carets, Unicode input, and combinations of metacharacters. - Do not treat the output as security-grade sanitization without validating the final value against an explicit allowlist. ]]>

SkillSpector

Vulnerability Patterns

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

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The manifest description says to use the skill whenever you need to 'transform, format, or manipulate strings,' which is a very broad activation condition for a markdown/manifest file. It does not provide narrower trigger boundaries, examples of when not to invoke it, or context constraints, increasing the chance of unintended invocation during ordinary text-related requests.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The manifest description says the skill 'Provides string manipulation and transformation operations for working with text,' which is a very general capability statement rather than a specific trigger scope. In a manifest file, this broad phrasing can overlap with many common text-editing requests and does not clarify when the skill should or should not activate.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.