writing-shape
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests raw material from user-provided files which could contain adversarial instructions intended to influence the agent's behavior.
- Ingestion points: The skill reads an input markdown file in full to "mine" it for content (SKILL.md).
- Boundary markers: No specific delimiters or instructions to ignore embedded commands within the input file are defined.
- Capability inventory: The skill is limited to reading files and appending content to a designated article file. It does not possess network access, shell command execution, or dynamic code evaluation tools.
- Sanitization: Input content is paraphrased or reworked into the article, but no explicit sanitization or filtering of instructions is mentioned.
Audit Metadata