supply-chain-security
Fail
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill references installation of security tooling from the official Anchore repository via shell script execution. This is a common industry pattern for distributing DevOps tools and originates from a well-known source. \n- [COMMAND_EXECUTION]: The skill instructs the agent to execute various command-line tools such as 'syft', 'grype', and 'cosign' to perform security audits and manage software artifacts. \n- [PROMPT_INJECTION]: The skill workflows involve scanning and processing external project files and container images, which creates a surface for indirect prompt injection. Malicious instructions could be embedded in the metadata of dependencies being analyzed. \n
- Ingestion points: File system and container image scanning via 'syft' and 'grype' as documented in SKILL.md. \n
- Boundary markers: Absent; the skill does not define specific markers or instructions to disregard embedded content in scanned artifacts. \n
- Capability inventory: Extensive shell command execution capabilities for security auditing and artifact management within SKILL.md. \n
- Sanitization: Absent; no explicit validation or sanitization of tool outputs is specified before processing by the agent.
Recommendations
- HIGH: Downloads and executes remote code from: https://raw.githubusercontent.com/anchore/syft/main/install.sh - DO NOT USE without thorough review
Audit Metadata