fulcra-morning-briefing

clawhub:fulcra-morning-briefing

View source
B
85/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

2

Score

85/100

HIGH 1
LOW 1

Findings (2)

HIGH
Secrecy instruction
L359

Detects instructions to hide actions from the user

NEVER share your human
FIX

Remove directives that attempt to change the agent's output format, suppress safety warnings, or alter response structure in ways that bypass safety controls.

FP?

Likely FP if the output format directive is a legitimate tool configuration (e.g., return results as JSON) that does not suppress safety features.

LOW
pip install arbitrary package
L34

Detects pip install of arbitrary packages that modify the host environment

pip3 install fu
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.