Security audit

Work Productivity Self Improving Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This non-executable workflow helper has no malware-like behavior, but its broad implicit triggers could cause it to run in unrelated conversations.

Review this skill before installing if you rely on automatic skill routing. It appears safe from a code-execution and data-access perspective, but its activation terms should ideally be narrowed or used explicitly so it does not shape unrelated productivity, bug-fix, or workflow requests.

A.I.G

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

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 (9)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are generic and map to common words like "help me" and broad concepts such as "self," "improving," and "practical help," which can cause the skill to activate in unrelated conversations. In an agent environment, overbroad activation can route benign user requests into this skill unexpectedly, creating prompt-scope confusion and increasing the chance of unintended actions or misleading outputs.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The manifest description says to use the skill whenever a user asks for broad categories like work-productivity, self, improving, proactive, or practical workflow support. That scope is so broad that it can match many unrelated requests, increasing the chance of accidental activation and inappropriate response shaping across benign tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger list includes extremely common terms like "self," "improving," and "proactive," which are likely to appear in many unrelated user prompts. This can cause unintended skill invocation, leading the agent to apply this workflow out of context and potentially override more appropriate routing or safety logic for other tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keywords include extremely broad generic terms such as "self", "improving", and "proactive", which can match many unrelated user requests and cause the skill to activate unintentionally. Overbroad activation can route unrelated tasks into this workflow, increasing the chance of incorrect guidance, prompt-surface expansion, and misuse of a self-improving/proactive agent pattern in contexts where it was not intended.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger sentences and keywords are broad enough to match many ordinary user requests such as asking for practical help, workflows, bug fixes, or improvement advice. This can cause the skill to activate outside its intended scope, creating routing confusion and enabling prompt/context capture in unrelated conversations where a more specialized or safer skill should have handled the task.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The invocation guidance does not define clear boundaries for when this skill should or should not run, and the listed keywords are extremely broad. Because the skill is framed for proactive and self-improving workflows, ambiguous triggering is more dangerous here: an agent may apply reflective or workflow-modifying behavior outside the user's actual intent, leading to unauthorized scope expansion or incorrect task routing.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger phrases are very broad and include common terms like "self," "improving," and "proactive," which can cause the skill to activate for many unrelated everyday requests. In an agent environment, over-broad activation can route users into an unintended workflow, leading to confusing behavior, prompt hijacking surface expansion, or accidental execution of actions under the wrong skill context.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The skill description defines usage conditions very broadly, including vague categories like work-productivity and practical workflow support, without a clear boundary for when the skill should or should not activate. This ambiguity makes accidental invocation more likely and can cause the skill to apply in contexts outside its validated scope, reducing reliability and increasing the attack surface for unintended behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The default prompt uses a long, generic natural-language activation phrase tied to common terms like 'help me', 'work', 'self-improving', and 'practical help', which can overlap with ordinary user requests. Because implicit invocation is enabled, this increases the chance the skill will auto-trigger unexpectedly, causing prompt-scope confusion, unintended tool behavior, or injection of this skill's instructions into unrelated conversations.
Content: No source excerpt is available for this finding.