Security audit

Work Productivity Pollyreach Gives Workflow Helper

Security checks for vulnerabilities and agentic risk

Overview

This is a documentation-only workflow helper with overly broad activation wording, but no executable code, credential use, persistence, or hidden data flow was found.

Before installing, be aware that this skill may trigger on ordinary words like phone or number if implicit invocation is used. It is best suited for explicit PollyReach-style workflow planning or hardening tasks; disable implicit invocation or narrow its triggers if you want predictable routing.

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 (13)

Vague Triggers

High

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The invocation description says to use the skill when a user asks for broad concepts like work-productivity or needs any practical workflow, artifact, checklist, analysis, or implementation support for this requirement. This ambiguous activation language makes the skill eligible for an overly wide range of prompts, which can lead to accidental invocation and misrouting of sensitive or unrelated tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger keyword list is excessively broad and includes generic terms like "every," "phone," "number," "ability," and "things," which can cause the skill to activate for unrelated user requests. Over-broad activation creates prompt-scope confusion and increases the chance this skill is invoked in contexts it was not designed for, potentially interfering with safer or more appropriate skills.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The trigger keyword list includes extremely broad everyday terms such as “every”, “phone”, “number”, “ability”, “things”, and “done”, which can cause the skill to activate for many unrelated user requests. This creates prompt-routing ambiguity and may expose users to irrelevant or unsafe workflow guidance when they did not intend to invoke this skill.
Content: No source excerpt is available for this finding.

Vague Triggers

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The trigger examples include very broad, ordinary language tied to common words like "phone," "gives," and generic help phrasing, which can cause the skill to activate for unrelated user requests. In an agent ecosystem, unintended invocation can route users into the wrong workflow, causing confusing behavior, irrelevant automation, 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: 91% confidence
Finding: The invocation guidance does not define when the skill should and should not be used, and the listed keywords are broad enough to overlap with normal productivity, phone, or bug-fix requests. In an agent ecosystem, ambiguous routing increases the chance this skill will intercept unrelated tasks, causing unsafe automation, degraded reliability, and confusing behavior across skills.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrase includes extremely generic terms and malformed broad text that can match ordinary user language rather than a clearly scoped task invocation. This can cause the skill to activate unintentionally, leading to prompt hijacking of unrelated conversations, incorrect workflow insertion, or bypass of intended user choice about when the skill should run.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The keyword list contains highly generic terms such as 'every', 'phone', 'number', 'ability', and 'things', which are likely to appear in many unrelated conversations. This can cause unintended skill selection and broaden the skill’s effective scope beyond what users intended, reducing safety and predictability.
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 broad natural-language prompts that can match ordinary user requests unrelated to this skill, causing accidental activation. In an agent ecosystem, overbroad routing can misapply workflows, confuse users, and increase the chance that the wrong skill handles sensitive or operational tasks.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The example trigger phrases are generic and effectively instruct activation for vague requests such as "Help me" or "I need a practical workflow" with only partial contextual anchoring. These examples reinforce unsafe routing behavior by training users or downstream systems to treat ordinary language as sufficient to invoke the skill.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The description says to use the skill when users mention broad terms like work-productivity, pollyreach, gives, every, or phone, but it does not clearly define exclusion criteria or the minimum context needed for activation. This unclear activation boundary increases the chance of accidental invocation, misrouting user intent, and delivering responses outside the skill’s appropriate scope.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The default prompt trigger is overly broad and includes generic terms such as "help me" and common workflow-related phrasing, which can cause unintended implicit invocation of the skill. Because implicit invocation is enabled, normal user requests unrelated to this specific skill could activate it unexpectedly, increasing the chance of prompt hijacking, incorrect tool routing, or unnecessary exposure of the skill's instructions and behavior.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The activation examples are underspecified and do not define when the skill should not run, so the routing logic may match on vague requests that only partially resemble the intended use case. This increases the chance of over-broad skill selection, which can mislead users, interfere with safer/more relevant skills, and create a larger attack surface for prompt-routing abuse.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 78% confidence
Finding: This Chinese README contains core descriptive content in English, which suggests a language presentation choice that is not explicitly offered to the user or justified as region-specific. The file does not state that users may choose their preferred language or explain why mixed-language content is required.
Content: No source excerpt is available for this finding.