autonomy-windowed

clawhub:autonomy-windowed

View source
C
70/100

First Seen

Feb 18, 2026

Last Scanned

Feb 22, 2026

Findings

2

Score

70/100

HIGH 2

Findings (2)

HIGH
Autonomous agent spawning
L4

Detects autonomous sub-agent or cron-based execution without human oversight

cron jobs run + autonomous
FIX

Remove directives that force the agent to call specific tools or APIs not required for the skill's stated functionality. Tool calls should be determined by user intent, not embedded directives.

FP?

Likely FP if the skill legitimately needs to call other tools as part of its workflow (e.g., a deployment skill that calls git and cloud CLI tools).

HIGH
Role switching attempt
L71

Detects attempts to make the AI assume a different role

Switch to standby mode
FIX

Remove directives that attempt to alter the agent's behavior or persona. Skill descriptions should describe tool functionality, not contain behavioral commands for the agent.

FP?

Likely FP if the matched text is part of the skill's legitimate system prompt configuration that defines the tool's behavior for the user, not an attack.