test-strategy

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute directory listing commands (ls) on various local paths (such as ~/.claude/skills/, ~/.agent/skills/, and ~/.agents/skills/) to identify which companion skills are currently installed.
  • [PROMPT_INJECTION]: The skill includes an automated 'Companion check' instruction that triggers upon first activation. This instruction directs the agent to enumerate the user's environment and conditionally suggest installing additional tools from the 'AbsolutelySkilled' repository, which is a behavioral instruction unrelated to the primary functionality of providing testing strategies.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 02:06 PM
Security Audit — agent-trust-hub — test-strategy