container-scan-hadolint

Pass

Audited by Gen Agent Trust Hub on Aug 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to run the hadolint command-line utility to perform static analysis on Dockerfiles.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data without safety boundaries.
  • Ingestion points: The agent ingests data from external Dockerfiles and the JSON output of the hadolint command.
  • Boundary markers: The instructions do not specify any delimiters or special handling to separate the content of the files being analyzed from the agent's task instructions.
  • Capability inventory: The agent utilizes shell command execution and file reading to perform its core functions.
  • Sanitization: There are no sanitization or validation steps provided for the external content before the agent summarizes it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 27, 2026, 06:48 PM
Security Audit — agent-trust-hub — container-scan-hadolint