Back to skill

Security audit

Progress Report

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Portuguese progress-report writer with minor usability concerns but no evidence of hidden or harmful behavior.

Install if you want Portuguese progress-report drafting. Be aware it may activate on generic activity lists and may use memory to recall prior report context or style preferences; avoid including sensitive work details unless you are comfortable with that context being used for future reports.

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill description, triggers, prompts, and output templates are all specified in Portuguese, including mandated prompts and formatting rules, without offering a language choice. This can violate language/locale policy when users have not explicitly opted into Portuguese or when the broader environment is multilingual.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The trigger list says the skill should invoke when the user simply 'Enviar uma lista de atividades'. Sending a list of activities is common in many contexts and does not clearly distinguish progress-report generation from other planning, task-tracking, or note-processing requests, which makes unintended invocation more likely.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.