Back to skill

Security audit

Financial Report Tracker

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed financial-report helper that fetches public market data and prints reports, but users should treat its investment-style recommendations cautiously.

Install and run this only in an isolated Python environment, preferably with reviewed pinned dependencies. Expect it to contact public market-data services for ticker data. Do not rely on its recommendations for trading or investing decisions, and be aware that the --quarter option does not appear to produce true quarter-specific analysis.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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 (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:16
Finding

Unpinned Third-Party Dependencies Create a Supply-Chain Risk

Content
View full analysis

Vulnerability Details

File Location: SKILL.md, lines 16–19
Vulnerability Type: Unpinned and unhashed third-party dependencies
Risk Level: Medium

Vulnerable Code:

markdown
Install Python dependencies before first use:
```bash
pip install yfinance requests pandas
text

### Technical Analysis
The installation instructions retrieve mutable package versions without version constraints, a lockfile, or cryptographic hash verification. Consequently, the installed code can change over time without any corresponding change to the reviewed project.

If a dependency release or its distribution account is compromised, following the documented command could install attacker-controlled code. Python packages can execute code during installation or later when imported by `scripts/earnings_tracker.py`. The direct `requests` dependency also appears unnecessary because it is imported but never used, expanding the dependency attack surface without providing functionality.

This finding does not establish that the named packages are currently malicious. The vulnerability is the absence of reproducible, integrity-verified dependency resolution.

### Attack Path
1. An attacker compromises a dependency maintainer account, package release process, or relevant distribution channel.
2. The attacker publishes a malicious release under one of the dependency names.
3. A user follows the documented `pip install yfinance requests pandas` command.
4. Pip resolves the mutable package name to the attacker-controlled release because no reviewed version or hash is required.
5. Malicious code executes during package installation or when the installed package is imported by the tracker.
6. The code operates with the permissions and environmental access of the user running pip or the tracker.

### Impact Assessment
Successful exploitation could execute arbitrary Python or native code with the privileges of the installing or execu
...[truncated 386 chars]
Remediation
View remediation

Remediation Suggestions

  1. Pin every direct dependency to a reviewed, exact version rather than installing unconstrained package names.
  2. Maintain dependencies in a lockfile generated through a reproducible workflow.
  3. Require cryptographic hashes during installation, such as with a hash-locked requirements file and pip install --require-hashes.
  4. Explicitly use the trusted official package index in deployment instructions and prevent unexpected fallback indexes.
  5. Remove requests as a direct dependency and import if it remains unused.
  6. Review transitive dependencies, monitor security advisories, and update pins through a controlled testing and approval process.
  7. Install dependencies in an isolated virtual environment under a non-privileged account.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (5)

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding

The skill advertises commands that install dependencies and run a Python script using network-capable libraries, but the manifest declares no explicit tool scope or permissions. That creates an authorization ambiguity where an agent or platform may invoke networked behavior without clear least-privilege boundaries, increasing the risk of unintended external data access or execution in environments that rely on metadata for enforcement.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The invocation text is broad enough to match generic finance conversations such as earnings, EPS, or company financials, which can cause the skill to trigger outside the user's intended workflow. In an agent setting, over-broad matching can lead to unnecessary network calls, irrelevant execution, or insertion of automated investment-style summaries into ordinary discussion, expanding the attack surface and creating consent and reliability issues.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The interface and usage text imply quarter-specific review support, but the quarter parameter is ignored throughout the implementation. This can mislead users into believing they are receiving analysis for a selected reporting period when the output is actually generic latest-available data, creating integrity and trust issues in financial decision support.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The script emits substantial user-facing analysis and recommendation text in English only, including investment-style guidance such as 'consider accumulating on dips' and 'wait for pullback opportunity', with no option to choose another language or locale. Under the stated policy, forcing a specific language without user opt-in is a natural-language policy violation.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill goes beyond neutral financial summarization and emits explicit trading-style recommendations such as 'consider accumulating on dips' and 'wait for pullback opportunity.' In an investment-focused skill, this is risky because users may treat the output as actionable financial advice despite the tool relying on simplistic heuristics and potentially incomplete Yahoo Finance data.

Content

No source excerpt is available for this finding.