story-import
Pass
Audited by Gen Agent Trust Hub on Aug 20, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a bundled Python script
scripts/tracking_commit.pyto manage project state, initialize tracking JSONs, and handle project structure migrations. It also invokes platform-specific commands like/story-long-analyzeand/story-setup. - [PROMPT_INJECTION]: The skill processes untrusted user-provided novel text (either from files or direct input) to generate summaries and structural metadata, which presents an attack surface for indirect prompt injection.
- Ingestion points: Untrusted novel content is ingested in
SKILL.md(Phase 1, Step 3) through file paths or pasted text. - Boundary markers: The instructions do not provide delimiters or warnings to isolate untrusted novel content when it is passed to deep analysis modules in Phase 2.
- Capability inventory: The skill can perform file system operations and execute bundled Python scripts.
- Sanitization: The
scripts/tracking_commit.pyscript performs string sanitization for filenames and JSON output (e.g., removing newlines and special characters), but it does not sanitize or filter the narrative content of the novel text itself.
Audit Metadata