clawtv

clawhub:clawtv

View source
F
21/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

12

Score

21/100

HIGH 1
MEDIUM 8
LOW 3

Findings (12)

HIGH
Read sensitive files and transmit externally
L139

Detects skills that both read sensitive credential files and send data to external services

read these credentials + send any data to external API
FIX

Block access to git credentials, SSH keys, and repository tokens. If git operations are needed, use scoped deploy keys and restrict the tool to specific repositories.

FP?

Likely FP if the match is documentation about git configuration (e.g., setting up git credentials helper) rather than code that reads and transmits them.

MEDIUM
Screenshot or screen capture with transmission
L30

Detects screenshot/screen capture tools combined with upload or transmission

screenshot + send any data to external API
FIX

Block the ability to read and transmit contents of configuration files (.env, config.json, settings.yaml). Implement file path validation to prevent access to sensitive config files.

FP?

Likely FP if the skill reads config files to configure itself locally without transmitting the contents externally.

MEDIUM
Shell profile modification for persistence
L67

Detects instructions to modify shell config files for environment persistence

add to your shell profile (~/.zshrc, ~/.bashrc
FIX

Avoid modifying shell profiles (.bashrc, .zshrc, .profile) programmatically. Instruct users to add PATH entries manually, or use a version manager (nvm, pyenv) instead.

FP?

Likely FP if the match is documentation showing how to add a tool to PATH manually, especially if it only appends to PATH without modifying other settings.

MEDIUM
Internal IP range access
L77

Detects references to private/internal IP ranges in URL context

http://192.168.1.100:
FIX

Implement URL allowlisting for all outbound requests. Block requests to private IP ranges (10.x, 172.16-31.x, 192.168.x), localhost, and link-local addresses.

FP?

Likely FP if the match is a localhost URL used for local development (e.g., http://localhost:3000) in setup documentation.

MEDIUM
Cross-tool data leakage
L139

Detects patterns where credential or secret reads are combined with external data transmission

read these credential + send any data to external
FIX

Prevent credentials and sensitive data obtained by one MCP tool from being passed to other tools. Implement data isolation between tools and restrict cross-tool data flow for secrets.

FP?

Likely FP if the cross-tool data flow is intentional API authentication (e.g., a tool fetches an auth token that another tool uses for the same service).

MEDIUM
Shell profile modification for persistence
L221

Detects instructions to modify shell config files for environment persistence

add to your shell profile (~/.zshrc, ~/.bashrc
FIX

Avoid modifying shell profiles (.bashrc, .zshrc, .profile) programmatically. Instruct users to add PATH entries manually, or use a version manager (nvm, pyenv) instead.

FP?

Likely FP if the match is documentation showing how to add a tool to PATH manually, especially if it only appends to PATH without modifying other settings.

MEDIUM
Internal IP range access
L229

Detects references to private/internal IP ranges in URL context

http://192.168.1.100:
FIX

Implement URL allowlisting for all outbound requests. Block requests to private IP ranges (10.x, 172.16-31.x, 192.168.x), localhost, and link-local addresses.

FP?

Likely FP if the match is a localhost URL used for local development (e.g., http://localhost:3000) in setup documentation.

MEDIUM
Internal IP range access
L468

Detects references to private/internal IP ranges in URL context

http://192.168.1.100:
FIX

Implement URL allowlisting for all outbound requests. Block requests to private IP ranges (10.x, 172.16-31.x, 192.168.x), localhost, and link-local addresses.

FP?

Likely FP if the match is a localhost URL used for local development (e.g., http://localhost:3000) in setup documentation.

MEDIUM
Shell profile modification for persistence
L504

Detects instructions to modify shell config files for environment persistence

add to ~/.zshrc or ~/.bashrc
FIX

Avoid modifying shell profiles (.bashrc, .zshrc, .profile) programmatically. Instruct users to add PATH entries manually, or use a version manager (nvm, pyenv) instead.

FP?

Likely FP if the match is documentation showing how to add a tool to PATH manually, especially if it only appends to PATH without modifying other settings.

LOW
Runtime URL controlling behavior
L87

Detects URLs fetched at runtime that control or influence agent behavior without pinning

Get your Plex token: https:// + config
FIX

Avoid loading configuration or behavior-controlling content from runtime URLs. Bundle required configurations locally or pin remote config to versioned, integrity-verified endpoints.

FP?

Likely FP if the URL in the match is a documentation link or example URL (e.g., example.com) rather than an actual runtime-fetched configuration endpoint.

LOW
External API response used without validation
L131

Detects patterns where external API responses are used directly without validation or sanitization

API cost and send no data + immediately when the use
FIX

Validate and sanitize all data received from external APIs before using it in tool operations or agent prompts. Implement schema validation and treat API responses as untrusted input.

FP?

Likely FP if the match is a truncated table cell or documentation fragment that mentions API responses in a descriptive context, not actual unvalidated data processing.

LOW
pip install arbitrary package
L185

Detects pip install of arbitrary packages that modify the host environment

pip install py
FIX

Pin all pip packages to exact versions (e.g., pip install package==1.2.3). Use a requirements.txt or pyproject.toml with pinned versions and hash verification.

FP?

Likely FP if the match is in documentation showing how to install the skill's own PyPI package.