account-management

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to use the ls command to inspect specific local directories (e.g., ~/.claude/skills/) to identify installed companion skills. This check is localized to the agent's own configuration paths and is used to suggest relevant functional expansions.
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing additional related tools using the npx skills add command from a third-party source (AbsolutelySkilled). This is presented as a standard method for extending the agent's capabilities within the supported platforms.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, such as customer annual reports and business goals, for creating account plans. While this represents a potential surface for indirect injection, the skill does not possess high-risk capabilities (like arbitrary code execution) that could be exploited by malicious data, and the behavior is typical for business analysis tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:05 PM
Security Audit — agent-trust-hub — account-management