inject
What this skill does
The skill is designed for context injection, automatically retrieving and formatting relevant knowledge from a database to enhance the Agent's responses. It is a system-level skill that is not directl
github/leoyeai - Data Exfiltration - 2.1k stars
Threat analysis
Skill info
pkg:github/LeoYeAI/openclaw-master-skills@e5199b5?skill=injectAssessments (2)
Data Exfiltration
Data Exfiltration via local-llm-review
scripts/inject.ts
The script connects to a local SQLite database (`.kivo/knowledge.db`) and retrieves knowledge entries based on user queries. If this database contains sensitive or private information, and the knowledInput Validation
Input Validation via local-llm-review
scripts/inject.ts
The script uses `process.argv` to parse command-line arguments without robust input validation. This could be exploited if malicious input is provided, potentially leading to unexpected behavior or inBadge
Add the Anomity scan badge for inject 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 inject? Report an issue or request a rescan.
