Back to skill

Security audit

Work Productivity Skillscan Security Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

The scanners report a benign skill with no AIG findings and one low-risk concern about broad activation keywords, which is why instruction scope is marked as a note.

The verdict is benign with high confidence, and Skillspector reported complete coverage of the six listed components. Consider whether broad activation could be inconvenient; the scan reported no other security issues, though a benign verdict does not guarantee zero risk.

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
  • 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 (6)

Activation keywords include common words without security-workflow scope constraints.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The usage keywords include everyday words such as every, must, pass, and before, which can occur in requests unrelated to SkillScan or security workflows. The README does not constrain these keywords to a domain-specific combination or provide exclusions, creating an overly broad invocation scope despite the more specific trigger sentences.

Content

No source excerpt is available for this finding.

Activation keywords include common words such as `every`, `must`, `pass`, and `before` without domain-specific constraints.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The usage section lists everyday words as keywords without requiring them to appear in a SkillScan security context. These words occur frequently in unrelated requests, making the activation scope ambiguous and potentially causing unintended invocations.

Content

No source excerpt is available for this finding.

Activation keywords include common everyday words without a SkillScan-specific scope restriction.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes standalone words such as every, must, pass, and before, which occur routinely in requests unrelated to SkillScan or security workflows. The description at line 4 similarly permits activation for broad keywords or generic implementation support, without requiring a SkillScan-specific context or providing exclusions.

Content

No source excerpt is available for this finding.

Activation keywords include common words without a SkillScan-specific scope restriction.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The keyword list includes everyday words such as every, must, pass, and before, which can occur in requests unrelated to SkillScan or security workflows. The description at line 4 also treats broad keywords as activation conditions, and no exclusion conditions constrain these matches.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled without a clear, actionable activation scope.

Medium
Category
Trigger Abuse
Confidence
90% confidence
Finding

The description states that users demand SkillScan-style workflows rather than specifying which requests this skill handles. With implicit invocation enabled, the generic references to fixing bugs and hardening leave it unclear whether ordinary debugging or security requests should activate the skill.

Content

No source excerpt is available for this finding.

Usage keywords include everyday words without activation constraints.

Medium
Category
Trigger Abuse
Confidence
92% confidence
Finding

The usage signals include standalone words such as "every", "must", "pass", and "before", which occur frequently in unrelated requests. Unlike the domain-specific trigger sentences below, these keywords have no stated requirement to appear alongside SkillScan-related context, making the activation scope overly broad.

Content

No source excerpt is available for this finding.