story-import
Pass
Audited by Gen Agent Trust Hub on Jul 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill ingests untrusted data in the form of novel text or files provided by the user (SKILL.md, Phase 1). This content is then used to populate metadata, generate project structures, and drive sub-agent workflows. Malicious instructions embedded within the novel text could potentially influence the agent's behavior during the analysis or migration phases.
- Ingestion points: User-provided text or file paths (Phase 1: Step 3).
- Boundary markers: The skill does not define explicit delimiters or 'ignore embedded instructions' warnings when processing the novel content.
- Capability inventory: The skill performs file system reads/writes, directory creation, and triggers other agent skills such as
/story-long-analyzeand/story-short-analyze. - Sanitization: There is no evidence of sanitization or filtering of the external novel content before it is interpolated into project templates or used to define character states and plot structures.
Audit Metadata