Security audit

职得Offer校园求职助手

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent job-search and interview-prep helper that calls a disclosed third-party API, with privacy and API-key handling considerations users should understand.

Install only if you are comfortable sending your recruiting searches, company/city filters, requested job or interview IDs, account quota checks, and API key to offer.yxzrkj.cn. Prefer the ZHIDE_OFFER_KEY environment variable over a local config file, and do not commit any real API key into a repository or shared skill directory.

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

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (9)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The README explicitly instructs users to copy a template into a local config file and place a real API key in it, but it does not warn about file permission hardening, accidental commits, backups, or other local credential exposure paths. While storing secrets locally is sometimes necessary, documenting this pattern without safeguards increases the likelihood of credential leakage, especially for users who may later version-control or share the skill directory.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The trigger phrases are broad, generic job-seeking terms such as 'offer', '找工作', and '面试准备', which are likely to appear in ordinary conversation. This can cause unintended activation of the skill and unexpected routing of user requests to this tool, increasing the chance that user queries are sent to an external service without clear intent or awareness.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill explicitly documents outbound requests to a third-party endpoint using an API key, but it does not clearly inform users that their search terms and potentially sensitive job-seeking interests will be transmitted off-platform. In a recruiting context, queries may reveal personal intent, employers of interest, interview preparation, or other sensitive behavioral data, so the lack of disclosure meaningfully increases privacy risk.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: This markdown file presents all user-facing instructions and API documentation exclusively in Chinese. Under the stated policy, forcing a specific language without user opt-in or documented justification is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 93% confidence
Finding: This JavaScript file contains natural-language comments and CLI output entirely in Chinese, including usage instructions and warnings, but does not indicate that the skill is China-specific or provide any language opt-in. Under the policy, forcing a specific language without user choice is a natural-language policy violation.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The module sends arbitrary tool arguments to a remote third-party endpoint over the network but provides no disclosure, consent gate, or data-classification checks before transmission. In an agent skill context, tool arguments can easily contain prompts, user inputs, files, tokens, or other sensitive business data, so silent exfiltration to an external service is a real privacy and security risk even though TLS is used.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The usage text and error message are presented in Chinese only, as shown by the command help and unknown-command output. This imposes a specific language on users without offering a language choice or documenting a justified locale restriction, which matches the policy-violation criteria for language or locale constraints.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 93% confidence
Finding: The file's user-facing natural language strings and usage instructions are entirely in Chinese, including the description and error message. Because there is no opt-in, alternative locale, or documented region-specific justification in this file, it constitutes a language/locale policy concern under the stated rule.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 97% confidence
Finding: The file’s natural-language content, including the header comments, usage examples, error message, and output text, is entirely in Chinese. For a general-purpose job search script, this imposes a specific language on users without any opt-in, fallback, or documented justification for the locale restriction.
Content: No source excerpt is available for this finding.