title-page
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external, user-supplied data such as screenplay titles, author names, and contact information to format them according to Fountain standards.
- Ingestion points: Metadata fields (Title, Author, Contact, Source, Notes) provided by the user during screenplay creation or updates (SKILL.md).
- Boundary markers: The skill does not define specific delimiters or instructions to the agent to disregard potentially malicious instructions embedded within the screenplay metadata.
- Capability inventory: The skill itself is purely instructional and does not invoke high-risk capabilities like network requests, file system writes, or subprocess execution.
- Sanitization: There are no explicit instructions for the agent to sanitize or validate the content of the metadata fields before processing or outputting them.
Audit Metadata