writing-for-agents
Pass
Audited by Gen Agent Trust Hub on Oct 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation includes an installation command (
npx skills add SirDarcanos/agentskills) that fetches the skill from the author's official GitHub repository. This is a standard distribution method for the SirDarcanos skill ecosystem. - [INDIRECT_PROMPT_INJECTION]: The skill's primary purpose is to ingest and modify external documentation and instruction files, which creates a potential surface for indirect prompt injection if those files contain malicious instructions.
- Ingestion points: The agent is instructed to read the full content of target documents (e.g.,
AGENTS.md,CLAUDE.md, or other skill files) as seen inSKILL.mdSection 1. - Boundary markers: No explicit instruction for using delimiters or boundary markers (such as XML tags or Markdown blocks with explicit 'ignore' warnings) is provided for the input processing phase.
- Capability inventory: The agent is authorized to read and write local files and potentially invoke other tools verified to be within the
SirDarcanos/agentskillsprovenance. - Sanitization: There are no specific requirements for the agent to sanitize or escape content from external files before it is processed or written back to the filesystem.
Audit Metadata