T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:59- Finding
Unvalidated User-Supplied URLs May Enable Server-Side Request Forgery
- Content
View full analysis
- Remediation
View remediation
Security audit
DoctorClaw Competitor Watch
Security checks for vulnerabilities and agentic risk
Overview
This is a competitor-monitoring skill whose web scanning, optional alerts, and local history are disclosed and fit its stated purpose.
Install this only if you want your agent to access competitor websites and social pages, keep historical snapshots, and optionally send reports to Telegram or Discord. Use a vetted list of public competitor domains, avoid internal or sensitive URLs, and set clear choices for delivery channels and snapshot retention.
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 (1)
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 (2)
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
The skill encourages scanning competitor websites and social profiles, sending reports via Telegram or Discord, and saving snapshots to local memory, but it does not clearly warn users about these external actions or the retention of collected data. This reduces informed consent and can cause users to unintentionally initiate outbound network activity, third-party data transfer, and persistent storage of monitoring results.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 95% confidence
- Finding
The example trigger "What are my competitors up to?" is broad, natural language that overlaps with ordinary conversation and can cause the skill to activate unexpectedly in unrelated contexts. Because this skill performs external monitoring, reporting, and persistence to local memory, accidental invocation can lead to unnecessary outbound requests, collection of third-party data, and unintended archival or notifications.
- Content