timeline-creator
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill features a workflow that ingests user-provided project details to generate an HTML document, creating a potential surface for indirect injection.
- Ingestion points: Project names, task lists, and milestone data extracted from user requests as described in the workflow section of SKILL.md.
- Boundary markers: Absent; there are no instructions to the agent to use delimiters or ignore instructions embedded within the extracted project data.
- Capability inventory: The skill utilizes file-writing capabilities to output the final report to the local file system (e.g., [project]-timeline.html).
- Sanitization: Absent; the provided templates and workflow instructions do not specify HTML escaping or data validation for user-provided strings before inclusion in the final HTML output.
Audit Metadata