Security audit

A Stock Monitor

Security checks for vulnerabilities and agentic risk

Overview

This skill describes a stock-monitoring system with recurring automated jobs, but the shipped artifact lacks the scripts those jobs would run, so users cannot verify the actual behavior before installation.

Review before installing. Do not create the cron job until the missing scripts are supplied and audited, install dependencies in an isolated environment with pinned versions, and confirm what data is sent to market-data providers or messaging services before enabling alerts.

A.I.G

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 (2)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:127
Finding: Unpinned Third-Party Dependencies Create Supply-Chain Risk
Content: View full analysis
Remediation: View remediation
Flask== ``` 2. Generate a hash-locked requirements file using a tool such as `pip-compile --generate-hashes`, and install with: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 3. Pin transitive dependencies through a lockfile and update them through a controlled review process. 4. Document the expected Python package index and warn against untrusted mirrors or extra indexes. 5. Install dependencies in a dedicated, non-privileged virtual environment: ```bash python3 -m venv .venv . .venv/bin/activate python3 -m pip install --require-hashes -r requirements.txt ``` 6. Remove `ccxt` unless it is required by included and reviewed functionality. If required, document its exact purpose and pin it like every other dependency. 7. Add automated dependency vulnerability and provenance checks to the release process. ]]>

other

Note

Location: SKILL.md:142
Finding: Documented Executables and Scheduled Task Target Missing Files
Content: View full analysis
/scripts && python3 smart_market_updater.py"}' ``` Additional documented commands target files that are not present: ```bash # Update full-market data python3 scripts/update_all_market_data.py # Calculate market sentiment python3 scripts/market_sentiment.py # Smart update during trading hours python3 scripts/smart_market_updater.py # Check trading time python3 scripts/is_trading_time.py # Short-term stock selection python3 scripts/short_term_selector.py # Medium- and long-term stock selection python3 scripts/long_term_selector.py # Enhanced medium- and long-term stock selection python3 scripts/enhanced_long_term_selector.py ``` The document also references a missing changelog: ```markdown See: [CHANGELOG.md](references/CHANGELOG.md) ``` ### Technical Analysis The audited project contains only `SKILL.md`. The referenced `scripts/` directory, Python programs, templates, and `references/CHANGELOG.md` are absent. The advertised stock analysis, Flask interface, market monitoring, and alert behavior therefore cannot be inspected or executed from the supplied artifact. The cron command creates a recurring cross-session action whose target does not exist at audit time. Although the scheduled behavior is explicitly disclosed and aligned with the stated purpose, creating a persistent task before validating its executable target is ...[truncated 1771 chars]
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The skill explicitly promotes automated market-data collection and alerting, including cron-driven background execution and outbound notifications, but it does not disclose what data may be transmitted to third-party providers or messaging platforms, nor the operational impact of continuous polling. In a finance-related monitoring skill, this omission can cause users to unknowingly expose watchlists, trading interests, infrastructure metadata, or generate excessive network/API activity that affects reliability, quotas, or compliance expectations.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.