Back to skill

Security audit

English Phonetics Batch

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward batch English phonetics tool that reads user-provided word files, queries a disclosed dictionary API, and writes user-chosen output files.

Install only if you are comfortable sending the words in your input files to the public Dictionary API. Avoid using sensitive internal vocabulary lists, choose output paths carefully to avoid overwriting files, and consider pinning the requests dependency before production use.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (10)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill explicitly describes reading input files, writing output files, and making network requests to a free dictionary API, but it does not declare any tool scope such as permissions or allowed-tools. This creates an authorization and transparency gap: an agent or reviewer cannot easily constrain or audit the skill's file and network access, increasing the risk of unintended data exposure or overbroad execution.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The markdown repeatedly states that the skill adds and prioritizes '美式国际音标' / American IPA, including '美式发音优先,自动优先选择美式音标'. This is a natural-language locale policy concern because the skill enforces a specific pronunciation locale by default without indicating user choice or opt-in.

Content

No source excerpt is available for this finding.

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · references/usage-examples.md (reported line 177)May include surrounding context.

apple [noun] /something/ banana (noun) /something/

text
Automatically removes existing brackets/phonetics and re-processes clean.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module description states that the tool is specifically for English words and supports American English pronunciation, and the implementation consistently extracts American phonetics only. This is a natural-language locale constraint without any user opt-in or alternative locale selection, which can violate language/locale policy requirements.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
88% confidence
Finding

The script sends every processed word to a third-party API over the network, which can expose sensitive or proprietary word lists if users supply internal data. In this skill context, batch processing increases the volume of outbound data and there is no consent prompt, allowlist control, or offline mode, making unintended data exfiltration more likely.

Content

Scanner excerpt · scripts/english_phonetics_batch.py (reported line 47)May include surrounding context.

python
self.delay_ms = delay_ms
        self.max_retries = max_retries
        self.session = requests.Session()
        self.base_url = "https://api.dictionaryapi.dev/api/v2/entries/en/"
        self.stats = {
            "total": 0,
            "success": 0,

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown explicitly states that the skill prefers American pronunciation when available. Because the file does not offer a language/locale choice or frame this as an optional or region-specific behavior, it constitutes a locale policy concern under the natural-language policy rule.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
89% confidence
Finding

This markdown file repeatedly shows commands and API calls that create or replace output files such as output.txt, fixed_vocab.txt, and my_words.*, but it does not include any caution about overwriting existing files or choosing safe destinations. For markdown files, SQP-2 applies when the description omits warnings about behaviors that could affect user data or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

The examples discuss request delays, retries, rate limiting, and API safety, which strongly indicates the tool sends queried words to an external service. The markdown does not warn users that input words may be transmitted over the network, which is a relevant privacy disclosure for markdown under SQP-2.

Content

No source excerpt is available for this finding.

Unpinned Dependencies

Low
Category
Supply Chain
Confidence
96% confidence
Finding

The dependency specification uses a lower-bound only constraint (requests>=2.20.0), which allows installation of any future version and does not ensure reproducible or reviewed builds. This can expose the skill to vulnerable or breaking releases of requests, and also makes it impossible to verify whether a safe version is consistently deployed.

Content

Scanner excerpt · requirements.txt (reported line 1)May include surrounding context.

text
requests>=2.20.0

Unverifiable Dependency: requests has 16 known advisory(ies) (CVE-2014-1830 (Exposure of Sensitive Information to an Unauthorized Actor in Requests); CVE-2024-47081 (Requests vulnerable to .netrc credentials leak via malicious URLs); CVE-2024-35195 (Requests `Session` object does not verify requests after making first request wi) +13 more), but the manifest does not pin a version, so it is unknown whether the installed release is affected

Low
Category
Supply Chain
Confidence
90% confidence
Finding

Because requests is not pinned, the manifest does not demonstrate whether deployment will use a version affected by known advisories or a patched release. In a skill that likely performs automated lookups over network resources, use of a vulnerable HTTP client library could contribute to credential leakage, TLS/verification issues, or other request-handling weaknesses depending on runtime behavior.

Content

No source excerpt is available for this finding.