user-story-mapping-workshop
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external, potentially untrusted project data to generate its mapping outputs.
- Ingestion points: The
InputandStep 0sections ofSKILL.mdexplicitly instruct the agent to ingest "pasted context dumps," "PRD drafts," "website copy," and "user research" from the user or via invocation arguments. - Boundary markers: The skill does not define or use any boundary markers (such as XML tags or specific delimiters) to isolate this untrusted input from the agent's core facilitation instructions, which may allow embedded prompts to influence agent behavior.
- Capability inventory: The skill's capabilities are focused entirely on markdown generation and narrative structuring. No dangerous operations, such as network exfiltration, file system writes, or command execution, were identified across
SKILL.mdortemplate.md. - Sanitization: The skill lacks any instructions for the agent to sanitize or validate the provided context for malicious prompt patterns before processing it into the workshop output.
Audit Metadata