writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided markdown files ("raw material") that serve as an external data source which could contain malicious instructions.
- Ingestion points: Reads a markdown file provided by the user, as described in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore instructions" tags to separate the raw input content from the agent's task instructions.
- Capability inventory: The skill is limited to reading, appending, and editing markdown files. It does not have access to the network, shell commands, or sensitive system files.
- Sanitization: The skill does not perform any validation, filtering, or sanitization of the content found in the raw material file before processing it.
- [NO_CODE]: The skill contains only instructional text and configuration files. It does not include any executable scripts, binaries, or complex automation logic, which significantly reduces its attack surface.
Audit Metadata