Security audit

Weekly Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Git-based weekly report generator, with a limited markdown-output risk but no hidden or malicious behavior found.

Install only if you are comfortable with the skill reading repository history and writing a Markdown report that may include author names, commit messages, dates, and file-change details. Review generated reports before sharing them, and use a Markdown viewer that disables raw HTML or remote images if you process commits from untrusted contributors.

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/generate-report.ps1:48
Finding: Unescaped Git Metadata Allows Markdown Report Injection
Content: View full analysis
Remediation: View remediation
", ">" return $Value } $who = ConvertTo-SafeMarkdownCell $parts[2] $msg = ConvertTo-SafeMarkdownCell $parts[3] ``` 4. If reports are rendered as HTML, configure the Markdown renderer to disable raw HTML and remote resource loading. 5. Add tests containing pipes, `||`, newlines, links, image syntax, HTML tags, and backticks in author names and commit subjects. Verify that each value remains confined to one table cell and is displayed only as inert text. ]]>

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 (4)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 88% confidence
Finding: The description says to use the skill when the user asks for a "weekly report, work summary, progress review, or sprint recap," which includes broad phrases like "work summary" and "progress review." Without clearer constraints or exclusion examples, the trigger scope may overlap with many ordinary requests that are not specifically about generating reports from repository activity.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The template hard-codes Chinese headings and labels such as "周报", "报告周期", and "本周完成" while the rest of the skill is described in English. This may impose a specific output language by default without offering the user a language preference or documenting why that locale is required.
Content: No source excerpt is available for this finding.

Missing User Warnings

Low

Category: Not specified by scanner
Confidence: 84% confidence
Finding: This is a markdown file, so SQP-2 applies to omissions in the skill description. The examples demonstrate generating weekly-report.md and include commit hashes, author names, dates, and messages, but the document does not warn users that repository history and contributor information may be gathered and saved to an output file.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: SQP-3 applies to all file types and includes language or locale policy violations. The example uses a Chinese user request as the only invocation example, which can imply a language expectation without any opt-in, alternative language examples, or justification for a locale-specific constraint.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.