Security audit

Signature Extractor

Security checks for vulnerabilities and agentic risk

Overview

This skill is a local signature image-cleanup tool with some dependency and input-size hygiene risks but no hidden or unrelated behavior.

Install only in an environment where running pip packages is acceptable, preferably a virtual environment, and avoid processing untrusted images with very large dimensions or extreme scale values.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/extract_signature.py:88
Finding: Unbounded Image Scaling Can Cause Resource Exhaustion
Content: View full analysis
Remediation: View remediation
MAX_OUTPUT_PIXELS: raise ValueError("Requested output image exceeds the maximum pixel limit") ``` ]]>

T08 · Insecure Dependencies

Note

Location: SKILL.md:58
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

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 (1)

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: The activation and mode-selection guidance explicitly mixes English and Chinese trigger phrases, but the document does not say this is optional, user-selected, or limited to a region-specific deployment. Under the policy rule, hard-coded language handling can be a natural-language locale policy concern when no opt-in or justification is provided.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.