convert-to-devto
Pass
Audited by Gen Agent Trust Hub on Oct 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input through the
{{args}}placeholder. While the skill's purpose is limited to text transformation, it lacks clear boundaries to prevent the agent from executing instructions found within the input content. - Ingestion points: Arbitrary Markdown content is loaded into the agent's context via
SKILL.md. - Boundary markers: The input is enclosed in
<input_markdown>tags, but there are no instructions telling the agent to ignore commands within that block. - Capability inventory: The skill performs text editing only; it does not use any external tools, network capabilities, or file system write access.
- Sanitization: No sanitization or filtering is applied to the input content to prevent it from influencing the agent's behavior.
Audit Metadata