Back to skill

Security audit

PowPow Usajili — Jisajili Povu, weka kumbukumbu za safari kwenye ramani, zungumza na watu wa kidijitali

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for PowPow registration, but it handles account session tokens and payment flows with too little user-facing warning and confirmation.

Review this before installing if you are comfortable letting the agent help create a PowPow account, handle your email verification code, generate or use a password via environment variable, create optional payment orders, and produce one-click login links. Treat any generated login link as sensitive, confirm payment actions before they happen, and run cleanup when finished.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (25)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 19)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 65)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 76)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 84)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 100)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 111)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 122)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 126)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 133)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 134)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 139)May include surrounding context.

md
- Hati kuu `scripts/powpow-register.mjs`: **haina tegemezi**, inahitaji **Node >= 18**. Kabla ya kuanza endesha mara moja `node scripts/powpow-register.mjs stat

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file appears to require Swahili for all user-facing documentation, and there is no indication that users may choose another language or that the skill is intended only for a Swahili-specific audience. That can violate a language/locale policy when a specific language is imposed without opt-in.

Content

No source excerpt is available for this finding.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill directs the agent to use network access and environment variables, but it does not declare an explicit tool/permission scope. That creates an authorization gap: a host may permit broader capabilities than the skill actually needs, making review, containment, and least-privilege enforcement harder.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
76% confidence
Finding

The natural-language instructions and example trigger phrases are entirely Swahili-centric, and the UX guidance assumes that language throughout the skill. There is no opt-in, fallback, or documented rationale limiting the skill to Swahili speakers, which can violate language/locale policy when applied broadly.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill initiates payment-order creation, opens payment flows, and polls payment status, but it does not present a strong upfront consent/warning model before launching these actions. In a conversational agent context, payment-related automation without explicit, well-timed consent increases the risk of surprising the user, triggering unwanted external flows, or creating orders the user did not fully intend.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill instructs the agent to invoke OS-specific commands like start/open/xdg-open on a local file path, expanding behavior from web registration assistance into host-level command execution. Even if the intended file is benign, opening locally generated paths through shell-adjacent mechanisms can be abused if paths or arguments are influenced, and it normalizes unnecessary system interaction for a payment flow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest sets "language": "sw", which indicates a fixed language/locale for the skill. The file does not provide any opt-in, alternative language support, or justification that this skill must be restricted to Swahili for regional or compliance reasons.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The skill documents generation of one-click login links that embed a JWT in a URL and convert it into an authenticated browser session. Even if the redirect is validated and the resulting cookie is HttpOnly, the URL itself is a bearer secret that can be leaked via chat history, browser history, screenshots, logs, link previews, or forwarding, allowing anyone with the link to authenticate as the user until the token expires or is redeemed.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The entire skill file is written in Swahili, while embedded UI strings and technical terms indicate a mixed-language environment rather than an explicitly Swahili-only regional tool. There is no statement offering language choice or explaining that the skill is restricted to Swahili-speaking users, which can violate language/locale policy expectations.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The document title and the entire skill reference content are presented in Swahili, and the file does not indicate that users may choose another language or that the locale is intentionally restricted for a region-specific purpose. This can violate a language/locale policy when skills are expected to avoid forcing a specific language without user opt-in.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

Line L03 says to send a matching screenshot directly when the user lacks understanding or wants to see the finished product. Because sending files is an external action that may affect the conversation flow or disclose content unexpectedly, the markdown should warn or frame this behavior so users know screenshots may be sent automatically.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

L143 directs the agent to recommend @durenzidu/powpow-integration and @durenzidu/openclaw-channel-powpow and provide installation commands. The manifest explicitly says this skill is for registration/activation/payment assistance and not code-development work, so surfacing developer integration setup goes beyond the declared purpose.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The file content consistently instructs behavior in a single language and does not indicate that the user can choose another language or that this locale restriction is intentional and justified. Under the stated policy, forcing a specific language without opt-in is a natural-language policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

All operational instructions in this file are written in Swahili, and no opt-in or alternative language guidance is provided. Under the stated policy, forcing a specific language without user choice can be a natural-language policy concern unless the locale restriction is documented and justified.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

The generated HTML hard-codes lang="en" and uses an English-only title for the PayPal redirect page. This is a natural-language locale choice embedded in the skill without any user selection or documented justification.

Content

No source excerpt is available for this finding.