plot-consistency-checker
Pass
Audited by Gen Agent Trust Hub on Jul 6, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides instructions and templates for analyzing story consistency. It contains no executable scripts, network functionality, or sensitive file access. Patterns identified as risks in the included metadata report (e.g., shell backticks) are confirmed to be false positives caused by standard Markdown formatting within the documentation.
- [PROMPT_INJECTION]: The skill ingests untrusted user content such as manuscripts and character lists to perform its analysis, which constitutes a surface for indirect prompt injection.
- Ingestion points: User-provided story synopsis, chapters, and character data (SKILL.md, Step 1).
- Boundary markers: Absent. The skill does not instruct the agent to use delimiters when processing user content.
- Capability inventory: Limited to text generation, table creation, and reporting within the chat context.
- Sanitization: Absent. Narrative content is processed directly without filtering.
Audit Metadata