roadmap-backcast
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists exclusively of instructional documentation and templates for project management backcasting.
- [SAFE]: No external network requests, command executions, or sensitive file accesses are performed or requested by the skill.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a process for the agent to ingest and evaluate user-provided roadmap data against a rubric (
rubric_roadmap_backcast.json). While this creates a data ingestion surface, the skill does not provide the agent with any tools that could be abused through a malicious payload in the user input. - Ingestion points: User-provided roadmap content processed during the workflow steps in
SKILL.md. - Boundary markers: No specific delimiters or 'ignore' instructions are provided for the user input.
- Capability inventory: No scripts, tools, or shell commands are included in the skill package.
- Sanitization: No validation or filtering is performed on the ingested content beyond the agent's native guardrails.
Audit Metadata