T09 · Insecure Skill Coding Practices
Warning
- Location
SKILL.md:12- Finding
RescueTime API Credential Exposed Through Plaintext Storage and URL Query Parameters
- Content
View full analysis
- Remediation
View remediation
Security audit
RescueTime
Security checks for vulnerabilities and agentic risk
Overview
This skill is a straightforward RescueTime reporting helper, but users should treat the API key and returned activity data as private.
Install only if you are comfortable letting the agent query RescueTime for detailed activity reports. Keep the API key out of shared repositories and logs, prefer a protected environment variable or secret manager when possible, and ask the agent to confirm before fetching detailed app/site-level reports for broad or ambiguous requests.
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
- Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
- 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 (2)
Missing User Warnings
High
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The skill handles highly sensitive behavioral telemetry about app usage, time spent, and productivity patterns, but it does not warn the user that accessing this information involves querying a third-party service and exposing detailed computer-activity data. In ambiguous or delegated-use contexts, this lack of notice undermines informed consent and can lead to privacy violations or unexpected disclosure of sensitive work and browsing habits.
- Content
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 91% confidence
- Finding
The trigger description is broad enough to activate on common requests about daily activity, reports, or time tracking, which increases the chance the skill is invoked without the user clearly intending to access RescueTime data. Because RescueTime data reflects detailed computer-activity patterns, overbroad activation can cause unnecessary disclosure or use of sensitive behavioral information.
- Content
Static analysis
No suspicious patterns detected.