ton

clawhub:ton

View source
B
85/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

4

Score

85/100

HIGH 1
LOW 3

Findings (4)

HIGH
Zero-width character obfuscation
L1

Detects zero-width characters used to hide content


FIX

Remove hidden directives embedded in markdown, HTML comments, or encoded text. All agent-facing text should be explicit and visible in the skill definition.

FP?

Likely FP if the match is a standard markdown formatting pattern or HTML comment used for documentation rather than concealing directives.

LOW
Shell script file execution
L26

Detects execution of shell script files via bash/sh command or direct invocation

bash
scripts/ton-info.sh
FIX

Replace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.

FP?

Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.

LOW
Shell script file execution
L32

Detects execution of shell script files via bash/sh command or direct invocation

bash
scripts/ton-info.sh
FIX

Replace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.

FP?

Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.

LOW
Shell script file execution
L38

Detects execution of shell script files via bash/sh command or direct invocation

bash
scripts/ton-info.sh
FIX

Replace direct shell script execution with a language-native implementation or a sandboxed executor. If shell scripts must run, restrict them to a vetted allowlist with integrity checks.

FP?

Likely FP if the match references running a script that is part of the skill's own repository (e.g., ./setup.sh) with clear, auditable contents.