Back to skill

Security audit

Work Productivity Skill Vetter Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign with high confidence: the scans found no security alerts, while noting that broad activation wording could trigger it for unrelated requests.

The verdict is benign, with high confidence. Before installing, consider whether the broad activation wording could cause unwanted invocations; the scan reports no other security findings.

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 that can trigger unrelated requests.

Medium
Category
Trigger Abuse
Confidence
98% confidence
Finding

The usage keywords include everyday words such as 'first' and 'before', alongside broad terms such as 'github' and 'bug fix'. No matching constraints or exclusions restrict these keywords to skill-vetting requests, creating potential collisions with unrelated conversations.

Content

No source excerpt is available for this finding.

Activation keywords include common words unrelated to a specific skill-vetting request.

Medium
Category
Trigger Abuse
Confidence
96% confidence
Finding

The usage section lists keywords such as first, before, github, and bug fix, which can occur in everyday requests unrelated to skill vetting. It does not require these keywords to appear together or specify exclusions, leaving activation broader than the domain-specific example phrases.

Content

No source excerpt is available for this finding.

Activation keywords include common words and broad topics unrelated to skill vetting.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes everyday words such as first and before, as well as broad terms such as security and github. These can activate the skill for unrelated requests, and neither the description at L04 nor the trigger section requires a skill-vetting context or provides exclusion conditions.

Content

No source excerpt is available for this finding.

Activation keywords include ordinary words that can trigger the skill outside skill-vetting tasks.

Medium
Category
Trigger Abuse
Confidence
99% confidence
Finding

The trigger list includes everyday words such as first, before, and installing, alongside broad terms such as security and github. Neither this list nor the activation description on line 4 requires a skill-vetting context or supplies exclusions, so unrelated requests could activate this workflow.

Content

No source excerpt is available for this finding.

Implicit invocation is enabled, but the description does not define a clear activation scope.

Medium
Category
Trigger Abuse
Confidence
91% confidence
Finding

The short description is truncated, and the default prompt describes demand for Skill Vetter workflows rather than specifying what requests this skill handles. With implicit invocation enabled on line 7, these fragments do not clearly distinguish skill-vetting requests from general bug-fixing or hardening requests.

Content

No source excerpt is available for this finding.

Usage keywords include everyday words without activation constraints.

Low
Category
Trigger Abuse
Confidence
94% confidence
Finding

The usage signals include standalone keywords such as "first" and "before," as well as broad terms such as "security" and "github." These overlap with unrelated requests, and the file does not state that keyword matches must occur within a skill-vetting context, creating ambiguous activation scope.

Content

No source excerpt is available for this finding.