ejentum-reasoning-harness
What this skill does
The skill is a library of cognitive operations organized into four harnesses (reasoning, code, anti-deception, memory) that are exposed as MCP tools for agents to call when tasks match their trigger c
github/sickn33 - Data Exfiltration - 43.8k stars
Threat analysis
Skill info
pkg:github/sickn33/agentic-awesome-skills@11c9e67?skill=ejentum-reasoning-harnessAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
SKILL.md
The skill requires the user to provide an `EJENTUM_API_KEY` environment variable, which may contain sensitive information. If the API key is not properly secured, it could be exfiltrated or misused.Third-Party Dependency
Third-Party Dependency via local-llm-review
SKILL.md
The skill depends on the `ejentum-mcp` server, which is hosted externally. This introduces a potential risk if the third-party server is compromised or if the server's security practices are not robusBadge
Add the Anomity scan badge for ejentum-reasoning-harness 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 ejentum-reasoning-harness? Report an issue or request a rescan.
