ghostwriter
Pass
Audited by Gen Agent Trust Hub on Nov 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted source material (notes, transcripts, and outlines) as input for its writing tasks.
- Ingestion points: The skill explicitly mentions using "source material (notes, transcripts, outlines)" in the frontmatter description and Step 1 of the workflow.
- Boundary markers: There are no instructions to use delimiters (like XML tags or triple quotes) or warnings to ignore potentially malicious instructions embedded within the source material.
- Capability inventory: The skill is primarily designed for text transformation and editing. While no direct file-system or network operations are specified in these instruction files, the generated output influences the agent's response.
- Sanitization: No sanitization, validation, or filtering logic for external content is present.
Audit Metadata