assemble-lib-rules

Pass

Audited by Gen Agent Trust Hub on Sep 14, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes the opentaint health --rules command to retrieve and process a list of security rules.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data in the form of security rule definitions to generate project configurations, creating a potential surface for indirect injection.
  • Ingestion points: Reads files from .opentaint/tracking/rules/sources/ and .opentaint/tracking/rules/sinks/ as specified in the Workflow section of SKILL.md.
  • Boundary markers: The instructions do not define explicit delimiters or instructions to ignore embedded content within the ingested rule files.
  • Capability inventory: The skill performs file system write operations to the .opentaint/rules/ and .opentaint/tracking/ directories.
  • Sanitization: There are no explicit sanitization or validation steps for the content read from the rule files before it is interpolated into the generated YAML artifacts.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 14, 2026, 02:13 AM
Security Audit — agent-trust-hub — assemble-lib-rules