Security audit

Historical Data Manager

Security checks for vulnerabilities and agentic risk

Overview

This skill is a construction archive data-processing helper with expected file-reading and export behavior, but users should handle dependencies and spreadsheet exports carefully.

Install dependencies in an isolated environment with pinned reviewed versions, point the skill only at intended archive folders, and sanitize formula-like text before exporting legacy data to Excel or opening generated workbooks.

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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:417
Finding: Unpinned Third-Party Dependencies
Content: View full analysis
Remediation: View remediation
openpyxl== xlrd== pyodbc== ``` 2. Generate a lockfile that also constrains transitive dependencies. 3. Record and verify package hashes, and install with `pip --require-hashes`. 4. Explicitly configure an approved HTTPS package index rather than inheriting an unknown user or system configuration. 5. Regularly scan locked dependencies for known vulnerabilities and review upgrades before changing pins. 6. Install dependencies inside a non-privileged virtual environment or isolated container. ]]>

T09 · Insecure Skill Coding Practices

Warning

Location: SKILL.md:404
Finding: Spreadsheet Formula Injection in Excel Export
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 (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The manifest description says the skill can 'Extract, clean, and organize legacy construction data from archives' and 'Migrate historical project data, cost records, and schedules into modern formats,' but it does not define any specific trigger phrases, scope boundaries, or exclusion conditions. In a manifest file, this broad capability description can lead to ambiguous invocation because many ordinary data-processing requests in the construction domain could match.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 87% confidence
Finding: This markdown file includes executable example code that exports normalized data to 'historical_costs_normalized.xlsx'. While file creation is part of the skill's workflow, the surrounding documentation does not explicitly warn users that running the example will write a file to disk.
Content: No source excerpt is available for this finding.

Vague Triggers

Low

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The instruction 'When the user asks to convert or extract data' is broad and does not define narrower trigger boundaries or exclusions. In a markdown skill file, this can overlap with many ordinary requests and may cause unintended invocation because no negative examples or scope constraints are provided.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.