writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user-provided content as 'raw material' to generate articles.
- Ingestion points: Reads a markdown file containing raw material provided by the user (SKILL.md).
- Boundary markers: The instructions do not define delimiters or specific 'ignore instructions' prompts to wrap the ingested content, leaving a potential surface for instructions embedded in the raw material to be followed by the agent.
- Capability inventory: The agent is directed to read and write local files (SKILL.md). No network access, command execution, or dynamic code execution capabilities are present.
- Sanitization: There is no mention of sanitizing, escaping, or validating the raw material before processing.
Audit Metadata