Security audit

weekly-report-generator

Security checks for vulnerabilities and agentic risk

Overview

This is a simple weekly-report writing skill with no executable code or system access, but users should verify generated metrics and watch for broad auto-activation.

Install only if you want a passive writing helper for weekly reports. Review outputs carefully before sending, especially numbers, dates, completion percentages, business impact, customer impact, and technical details; replace anything not supplied by you with verified facts or placeholders.

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: SKILL.md:61
Finding: Unsupported Metrics and Impact Claims in Generated Reports
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 (2)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill is explicitly marked with always: true, which makes it eligible to activate regardless of user intent. For a writing-assistance skill with broad natural-language triggers, this can cause unintended invocation, context interference, or inappropriate transformation of unrelated workplace content, increasing prompt-scope and data-handling risk.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The trigger descriptions use common workplace phrases like 'status update' and 'weekly summary', which are broad enough to match many benign conversations that are not requests to transform content into a report. Combined with automatic eligibility, this ambiguity can lead to over-triggering and unintended processing of user content.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.