T09 · Insecure Skill Coding Practices
Error
- Location
SKILL.md:91- Finding
Temperature Coefficients Are Applied Without Converting Percent Values to Decimal Values
- Content
View full analysis
- Remediation
View remediation
Security audit
PV String design 光伏组串设计
Security checks for vulnerabilities and agentic risk
Overview
This skill is not malware, but it should be reviewed because its solar design calculations and automatic location-based lookups could lead to unsafe recommendations or unexpected data use.
Review this skill carefully before installing. It appears to be a documentation-only solar-design assistant rather than malware, but users should require independent engineering verification, explicit coefficient unit normalization, aggregate per-MPPT current checks, and confirmation before any external lookup using project location data.
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
Error
- Location
SKILL.md:68- Finding
Primary Inverter-Matching Workflow Checks Per-String Current Instead of Aggregate MPPT Current
- Content
View full analysis
- Remediation
View remediation
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 (3)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The auto-trigger keywords are broad enough to activate on common photovoltaic design requests without strong scoping or exclusion rules. That can cause the skill to run unexpectedly, collect detailed system/location inputs, and influence outputs in contexts where the user did not explicitly request this specialized workflow, increasing the risk of overreach or unintended data handling.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The skill directs automatic lookup of local extreme temperature data based on the project city/county, but does not instruct the agent to warn the user that location information may be used in an external query. This creates a privacy and transparency issue because sensitive project location details could be sent to third-party services without explicit user awareness or consent.
- Content
Missing User Warnings
Low
- Category
- Not specified by scanner
- Confidence
- 92% confidence
- Finding
The README states that the skill will automatically query local extreme temperatures, which implies external/network access and use of location data, but it does not warn users or document consent, source trust, failure modes, or privacy implications. In an agent setting, hidden outbound requests can surprise users, leak project location information, and cause the skill to rely on unverified third-party data for safety-critical electrical design calculations.
- Content
Static analysis
No suspicious patterns detected.