resolve-cve

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFE
Full Analysis
  • [DATA_EXPOSURE]: The skill reads dependency management files (pyproject.toml, uv.lock) to verify if the project is affected by a specific CVE. This is a standard and safe operation required for vulnerability assessment.
  • [EXTERNAL_DOWNLOADS]: The skill performs searches on the National Vulnerability Database (NVD) via WebSearch to retrieve CVSS scores. This utilizes a well-known and trusted security service to fulfill the skill's primary purpose.
  • [COMMAND_EXECUTION]: The skill executes local verification commands such as make verify, make check-types, and make test-unit. These are routine development practices used to ensure that code changes or dependency updates do not break the application.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from Jira issue summaries and descriptions. While this provides a theoretical surface for indirect prompt injection, the skill includes a mandatory 'GATE' instruction that prohibits the agent from proceeding with any modifications or Jira transitions without explicit user acknowledgment and confirmation.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 11:32 AM
Security Audit — agent-trust-hub — resolve-cve