outline-collaborator
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process user-provided story outlines, which constitutes a surface for indirect prompt injection.
- Ingestion points: The skill instructions in SKILL.md direct the agent to read existing outlines and user-shared story visions.
- Boundary markers: No specific delimiters or 'ignore embedded instructions' markers are defined for the AI when handling user-supplied text.
- Capability inventory: The skill has the ability to create and write markdown files (e.g.,
{project}-outline-{date}.md) and project configuration files (context/output-config.md,.outline-collaborator-output.md). - Sanitization: There is no evidence of input validation or sanitization for user-provided narrative content before it is processed or persisted to disk.
Audit Metadata