screenshot

skills-sh:openai_skills__screenshot

View source
B
85/100

First Seen

Feb 18, 2026

Last Scanned

Feb 20, 2026

Findings

6

Score

85/100

HIGH 1
LOW 5

Findings (6)

HIGH
Prompt cache poisoning
L28

Detects instruction override text in tool response content fields

cache prompt
FIX

Prevent MCP tools from modifying other tool definitions, system prompts, or agent configuration. Implement integrity checks on tool registration and block runtime tool modification.

FP?

Likely FP if the match is documentation about tool management features rather than a tool that actually tampers with other tools at runtime.

LOW
Shell script file execution
L31

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

bash <path-to-skill>/scripts/ensure_macos_permissions.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 <path-to-skill>/scripts/ensure_macos_permissions.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
L45

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

bash <path-to-skill>/scripts/ensure_macos_permissions.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
L122

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

bash <path-to-skill>/scripts/ensure_macos_permissions.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
L262

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

bash <path-to-skill>/scripts/ensure_macos_permissions.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.