T08 · Insecure Dependencies
Warning
- Location
requirements.txt:1- Finding
Unnecessary and Unpinned Third-Party Dependencies
- Content
View full analysis
- Remediation
View remediation
Security audit
Translational Gap Analyzer
Security checks for vulnerabilities and agentic risk
Overview
This skill is a local scientific report generator, but its install instructions and output-file handling create avoidable review-worthy risk.
Install only in an isolated environment and avoid running the dependency install unless the requirements are removed or pinned. Use --output only with a clearly workspace-local new file path, because the script does not enforce that restriction itself.
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/main.py:640- Finding
Unrestricted Output Path Allows Arbitrary File Overwrite
- Content
View full analysis
- Remediation
View remediation
Vulnerability Patterns
- Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
- Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
- MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (6)
Ae1
High
- Category
- analysis-evasion
- Confidence
- 100% confidence
- Finding
Referenced artifact was not completely inspected
- Content
md - `SKILL.md` - This file
Undeclared Tool Scope
Medium
- Category
- MCP Least Privilege
- Confidence
- 91% confidence
- Finding
The skill declares executable behavior that can write output files, but it does not define any explicit tool scope such as permissions or allowed-tools. That omission weakens containment and reviewability because an agent may be allowed to perform broader file operations than the skill documentation constrains, increasing the chance of unintended or unsafe writes if the packaged script or future edits behave unexpectedly.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 81% confidence
- Finding
The file presents multiple descriptions of the implementation surface that do not cleanly align: it describes a packaged script workflow, references editing in-file CONFIG values, claims only built-in libraries, and separately instructs installing requirements.txt. Inconsistent interface and dependency documentation is dangerous because operators may execute or trust the wrong path, bypass validation assumptions, or run additional code/dependencies not covered by the stated security controls.
- Content
Ae4
Medium
- Category
- analysis-evasion
- Confidence
- 80% confidence
- Finding
Suspicious Unicode normalization or mixed-script content
- Content
Unpinned Dependencies
Low
- Category
- Supply Chain
- Confidence
- 60% confidence
- Finding
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
- Content
text dataclasses enum
Unpinned Dependencies
Low
- Category
- Supply Chain
- Confidence
- 60% confidence
- Finding
Dependencies lack version pinning, allowing potential malicious package updates. Consider pinning versions.
- Content
text dataclasses enum