story-map-builder
Pass
Audited by Gen Agent Trust Hub on Nov 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided product requirements (Epics, Features, and Stories) and interpolates them into a self-contained HTML file. While it uses
html.escapefor text content, the resulting file is intended to be opened in a browser, and sophisticated injection patterns in the JSON data could attempt to bypass basic escaping or leverage the HTML structure to execute scripts (XSS). - Ingestion points: User-provided project names, epic names, feature names, story names, and descriptions via
data.jsonor stdin. - Boundary markers: None. The skill does not instruct the agent to ignore instructions embedded within the requirements data.
- Capability inventory: The skill has the capability to write files (
scripts/generate_story_map.pywrites the HTML output). - Sanitization: Uses Python's
html.escapefor most fields inscripts/generate_story_map.py, which provides basic protection but does not prevent all forms of web-based attacks if the output is used in sensitive contexts.
Audit Metadata