depot-container-builds

Pass

Audited by Gen Agent Trust Hub on Feb 22, 2026

Risk Level: SAFE
Full Analysis
  • [Prompt Injection] (SAFE): No instructions were found that attempt to override agent behavior, bypass safety guidelines, or extract system prompts.
  • [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, secrets, or sensitive file paths (like SSH keys or AWS configs) were detected. References to API tokens and project IDs use clearly labeled placeholders (e.g., <project-id>, <depot-token>, abc123). Network activity is restricted to legitimate container registry interactions (e.g., registry.depot.dev, public.ecr.aws).
  • [Obfuscation] (SAFE): The content is clear and readable. No Base64 encoding, zero-width characters, homoglyphs, or other obfuscation techniques were identified.
  • [Unverifiable Dependencies & Remote Code Execution] (SAFE): The skill does not attempt to install external packages or execute remote scripts via curl | bash. It describes the usage of a specialized CLI tool for its intended purpose.
  • [Privilege Escalation] (SAFE): No use of sudo, chmod 777, or other privilege escalation commands was found.
  • [Indirect Prompt Injection] (SAFE): While the skill involves processing build contexts and Dockerfiles, it does not create a surface for ingesting untrusted external data that would bypass agent safety logic. The capability inventory is limited to standard container build operations.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 22, 2026, 04:20 PM