T05 · Unauthorized Access and Privilege Escalation
Warning
- Location
SKILL.md:12- Finding
Unnecessary Filesystem Write Capability Violates Least Privilege
- Content
View full analysis
- Remediation
View remediation
Security audit
chromecast-control-free
Security checks for vulnerabilities and agentic risk
Overview
This skill appears intended for Chromecast control, but it asks for broader authority and gives inconsistent setup instructions that users should review before installing.
Install only if you are comfortable with an agent using shell commands to control LAN casting devices. Review or restrict the skill so it only runs catt commands for explicit device discovery, casting, playback, and volume requests; avoid providing API keys unless the publisher clarifies why they are needed, and do not open broad firewall port ranges without narrowing them to the target device and current session.
Vulnerability Patterns
- Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
- 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
Findings (2)
T09 · Insecure Skill Coding Practices
Note
- Location
SKILL.md:138- Finding
Overly Broad Firewall Port-Range Guidance Expands Host Attack Surface
- 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
- MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
- Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
- Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (7)
Vague Triggers
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The activation guidance says to use the skill whenever the user needs related functionality, without meaningful scoping constraints. For a skill with read/write/exec permissions and LAN device control, overly broad triggering can cause unintended invocation, network scanning, or command execution in situations where the user did not explicitly consent to those actions.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 98% confidence
- Finding
The main configuration section explicitly says the skill does not require any extra API key, but later support and installation sections instruct users to configure API keys and describe API authentication failures. This is an active contradiction in the skill documentation about how the skill is intended to operate.
- Content
Missing User Warnings
Medium
- Category
- Not specified by scanner
- Confidence
- 93% confidence
- Finding
The skill describes scanning the local network for devices and transmitting media URLs or local files to a target device, but it does not prominently disclose these privacy- and security-relevant side effects. In an agent context, undisclosed LAN discovery and content transmission can expose internal device names/IPs and leak local or remote media targets to other devices on the network.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 94% confidence
- Finding
The free-version scope repeatedly says seek/advanced control is unavailable, but the playback-control processing text includes 'skip' among supported commands. Elsewhere the document states seek/ffwd/rewind are full-version-only, so this supported-command list contradicts the advertised limits of the free edition.
- Content
Description-Behavior Mismatch
Medium
- Category
- Not specified by scanner
- Confidence
- 96% confidence
- Finding
The manifest positions the skill as a narrow Chromecast control tool, but later documentation expands scope to file processing, API integration, and generic command execution. This mismatch can cause overbroad invocation and unjustified user trust, increasing the chance that an agent grants the skill more authority or uses it for unrelated tasks involving local files, network access, or shell execution.
- Content
Intent-Code Divergence
Medium
- Category
- Not specified by scanner
- Confidence
- 97% confidence
- Finding
This Q&A answer says some functionality needs platform API keys, directly conflicting with the earlier statement that no extra API key is needed because the skill relies on local catt usage. The contradiction changes the user's understanding of the skill's operational model and required trust assumptions.
- Content
Natural-Language Policy Violations
Low
- Category
- Not specified by scanner
- Confidence
- 79% confidence
- Finding
Core user-facing metadata and instructions are primarily in Chinese, including the display name, summary, and description, while no language selection or locale scope is documented. This can violate a language/locale policy when the skill is presented to a broader audience without giving users an explicit choice.
- Content
Static analysis
No suspicious patterns detected.