check-docker-security
Pass
Audited by Gen Agent Trust Hub on Mar 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it analyzes untrusted data from local project files.
- Ingestion points: The skill reads external project files matching
**/Dockerfile*and**/docker-compose*.ymlvia grep-like patterns. - Boundary markers: There are no explicit instructions to use delimiters or ignore instructions embedded within the scanned Docker files.
- Capability inventory: The skill uses file search capabilities and generates detailed markdown reports based on the findings.
- Sanitization: No sanitization or validation of the content found in the project files is performed before it is processed by the agent.
Audit Metadata