writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [DYNAMIC_EXECUTION]: The file
references/verification_policy.mdprovides guidelines for the agent to generate and execute scripts (using PowerShell, Python, or Node.js) to verify that behavioral changes in the codebase or documents match the intended goals. - [INDIRECT_PROMPT_INJECTION]: As the skill is designed to audit and modify external instruction files such as
AGENTS.md,CLAUDE.md, and project-specific rules, it processes untrusted data which could potentially contain malicious prompts intended to influence the agent's behavior. - [COMMAND_EXECUTION]: The
references/verification_policy.mdandSKILL.mdfiles instruct the agent to run platform-appropriate commands to inspect the environment, such as checking for file existence or running test scripts, to provide factual evidence for its actions.
Audit Metadata