writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Sep 11, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a conceptual framework for agents to write more effective documentation. It does not contain executable code, remote script downloads, or network operations.
- [REMOTE_CODE_EXECUTION]: No remote code execution patterns were found. The skill references a local validator script (
.agent-skills/skill-standardization/scripts/validate_skill.sh) for project standards, but does not provide or invoke it directly. - [DATA_EXFILTRATION]: The skill does not access sensitive system paths (e.g., credentials, SSH keys) or utilize network-enabled tools like curl or wget.
- [INDIRECT_PROMPT_INJECTION]: While the skill provides instructions for the agent to create and modify documentation files using file-write tools, it is a meta-skill focused on writing style and clarity. It does not introduce logic for processing untrusted external data in a way that would facilitate prompt injection attacks.
Audit Metadata