Security audit

yanlin-company-filings

Security checks for vulnerabilities and agentic risk

Overview

This skill is a public Chinese-market company-announcement collector with disclosed network fetching, but users should treat its investment output as unverified because some sources are weakly attributed or fetched over HTTP.

Install only if you are comfortable with a script making outbound requests to public Sina Finance and exchange-related URLs. Treat the output as a screening aid, not verified investment advice; confirm important announcements directly from official HTTPS exchange or company disclosure pages before acting on them.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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

Findings (2)

T09 · Insecure Skill Coding Practices

Warning

Location: scripts/fetch_filings.py:173
Finding: Plaintext HTTP Fallback Permits Bulletin Data Manipulation
Content: View full analysis
Remediation: View remediation

other

Note

Location: scripts/fetch_filings.py:243
Finding: Static Exchange Records Are Presented as Collected Disclosure Data
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
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 (3)

Undeclared Tool Scope

Medium

Category: MCP Least Privilege
Confidence: 93% confidence
Finding: The skill explicitly instructs running a local Python script that performs multi-source data collection from Sina Finance and exchange disclosure sites, which implies network access, but the manifest does not declare any tool scope or allowed-tools. This creates an undeclared capability boundary: a host may permit broader execution than reviewers expect, reducing auditability and increasing the risk of unauthorized outbound requests or future abuse if the script is modified.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 92% confidence
Finding: The description and title are entirely in Chinese and present the skill as a Chinese-language skill, but there is no indication that users may choose another language or that the locale restriction is required. Under the policy, forcing a specific language without user opt-in 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: 96% confidence
Finding: The request header forces Accept-Language to zh-CN,zh;q=0.9,en;q=0.8, which imposes a specific locale policy in the skill behavior. This is a natural-language policy concern because the script does not offer user opt-in or configuration for language/locale selection, and no region-specific justification is documented in the file.
Content: No source excerpt is available for this finding.