sca-grype

Fail

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [Remote Code Execution] (CRITICAL): The skill directs the agent to install software by piping a remote shell script directly to 'sh' (https://raw.githubusercontent.com/anchore/grype/main/install.sh). This pattern allows for arbitrary code execution from a source not listed as trusted.
  • [External Downloads] (HIGH): The prerequisite installation script is fetched from the 'anchore' GitHub organization, which is not included in the pre-defined 'Trusted GitHub Organizations' list.
  • [Indirect Prompt Injection] (HIGH): The skill scans untrusted filesystems or container images and processes the output. Ingestion points: 'grype-results.json' produced by scanning external targets. Boundary markers: None used to delimit tool output. Capability inventory: Uses 'bash' for command execution and file operations. Sanitization: No validation of scan results before the agent interprets them for 'actionable upgrade paths'.
Recommendations
  • CRITICAL: Downloads and executes remote code from untrusted source(s): https://raw.githubusercontent.com/anchore/grype/main/install.sh - DO NOT USE
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 16, 2026, 01:35 PM