technical-writing-craft-weapon
Pass
Audited by Gen Agent Trust Hub on Jul 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is entirely informational, consisting of Markdown guides and templates to assist an AI agent in performing documentation reviews and ghostwriting tasks.
- [EXTERNAL_DOWNLOADS]: The skill references several external resources (e.g., diataxis.fr, developers.google.com, grafana.com, writethedocs.org) for research and methodology purposes. These references are for well-known and reputable technical documentation sources and do not involve the execution of remote code.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and analyze user-provided documentation. This creates an indirect prompt injection surface where a malicious document could contain instructions for the agent. However, as the skill lacks capabilities like network access, file system writes, or command execution, there is no viable path for exploitation. Evidence: (1) Ingestion points: User documents provided for review via 'SKILL.md' triggers. (2) Boundary markers: Absent. (3) Capability inventory: No tools or shell commands are utilized. (4) Sanitization: Absent.
Audit Metadata