story-long-write
Pass
Audited by Gen Agent Trust Hub on Jun 26, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses local shell commands to perform character counting and run included Node.js scripts for text formatting. These commands are utility-based and operate on local project files.
- Evidence in
SKILL.md:node scripts/normalize-punctuation.js,node scripts/check-ai-patterns.js, and Python one-liners for character statistics. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it reads and processes untrusted novel text from reference books and user drafts.
- Ingestion points:
SKILL.mddescribes reading files from对标/,拆文库/, and正文/directories. - Boundary markers: Absent. The skill does not use explicit delimiters to isolate untrusted text from instructions.
- Capability inventory: The skill can execute shell commands and spawn sub-agents.
- Sanitization: Absent. The skill interpolates the content directly into prompts for the writing agents.
Audit Metadata