Sentry skill-scanner
Scans installed agent skills for risky or malicious instructions and content.
🛡️ AgentReady threat assessment
MAESTRO 7-layer threat model + OWASP AIVSS risk score for Sentry skill-scanner, derived from its capabilities.
These scores are auto-generated from public information (the agent's own listing, docs, and repository) using the canonical OWASP AIVSS formula and the MAESTRO framework — an estimate for guidance, not a penetration test, audit, or certification. See the scoring methodology — every score is re-derived by the same automated method as an agent's public evidence changes.
Overview
A Sentry-published Agent Skill that inspects other installed skills for suspicious or dangerous instructions, bundled scripts, and prompt-injection risks. It encodes a review workflow over skill directories. Directly relevant to skill security since it reads and evaluates other skills' SKILL.md and scripts.
Key features and capabilities
- Skill security scanning
- Prompt-injection/risk detection
- Reviews bundled scripts
Use cases
- Vet a third-party skill before installing
- Audit installed skills for risk