.claude
What this skill does
The skill is a research agent that conducts web and local research, producing detailed reports with citations. It is designed for developers to understand, extend, debug, or integrate with GPT Researc
github/assafelovic - Data Exfiltration - 28.9k stars
Threat analysis
Skill info
pkg:github/assafelovic/gpt-researcher@5d84d2f?skill=claudeAssessments (3)
Data Exfiltration
Data Exfiltration via local-llm-review
references/config-reference.md
The configuration file contains API keys for various providers (OpenAI, Anthropic, Google, Groq, Azure OpenAI). If these keys are not properly secured, they could be exfiltrated or misused.Insecure Defaults
Insecure Defaults via local-llm-review
references/config-reference.md
The configuration includes default values for API keys (e.g., `OPENAI_API_KEY=sk-...`). This could be a security risk if users do not change these defaults.Configuration Management
Configuration Management via local-llm-review
references/config-reference.md
The configuration file includes a section for `.env` variables, which is a common practice but requires proper management to avoid exposure of sensitive information.Badge
Add the Anomity scan badge for .claude 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 .claude? Report an issue or request a rescan.
