dse-loop
What this skill does
Autonomous design space exploration for computer architecture and EDA (Electronic Design Automation). The skill runs a program, analyzes results, tunes parameters, and iterates until an objective is m
github/wanshuiyin - Tool Misuse - 14.5k stars
Threat analysis
Skill info
pkg:github/wanshuiyin/Auto-claude-code-research-in-sleep@bab594e?skill=dse-loopAssessments (2)
Tool Misuse
Tool Misuse via local-llm-review
SKILL.md
The skill's 'Safety Rules' explicitly prohibit destructive git operations such as `git reset --hard`, but the skill's allowed-tools include `Bash(*)`, which could be used to execute such commands if nExcessive Agency
Excessive Agency via local-llm-review
SKILL.md
The skill is described as autonomous and self-terminating based on an objective metric. This level of autonomy could be problematic if the objective is not well-defined or if the skill's behavior is nBadge
Add the Anomity scan badge for dse-loop to your README.
How Anomity governs this at runtime
Scan-time vetting tells you what a skill says it will do. Anomity's Endpoint Sensor sees what agents actually do: it discovers skills alongside every other AI artifact on the endpoint, and runtime governance can allow, deny, or log the tool calls a skill triggers. Policy violations route to your SIEM, Slack, email, or Jira, backed by a queryable 90-day audit trail.
Book a 30-minute demo to see your own skill inventory.
Methodology and disputes
Every skill is assessed by the Anomity Skill Intelligence engine against its public source; findings indicate risk patterns, not confirmed exploitation. Maintainer of dse-loop? Report an issue or request a rescan.
