skills/arthjean/skills/writing-beats/Gen Agent Trust Hub

writing-beats

Pass

Audited by Gen Agent Trust Hub on Sep 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied markdown files containing 'raw material' to generate content and write to the filesystem. * Ingestion points: The markdown file of raw material provided by the user. * Boundary markers: The instructions lack explicit delimiters or warnings to ignore instructions that might be embedded within the raw material. * Capability inventory: The skill has the ability to read from the filesystem and write the generated 'beats' back to an article file. * Sanitization: No input sanitization or validation of the content within the raw material is defined, meaning embedded instructions could theoretically influence the agent's output or file-writing behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 28, 2026, 11:05 AM