plot-consistency-checker
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted external data provided by the user, specifically story synopses, character lists, and manuscript chapters.
- Ingestion points: The 'Gather Story Information' phase (Step 1) in
SKILL.mdinstructs the agent to analyze user-provided content. - Boundary markers: The instructions do not define specific delimiters or clear directives for the agent to ignore potentially malicious instructions embedded within the story text.
- Capability inventory: The skill's capabilities are limited to text processing and generating analysis reports. There are no subprocess calls, file-write operations, or network requests across the instructions.
- Sanitization: There is no evidence of input validation or sanitization to filter out prompt injection strings from the manuscript data.
Audit Metadata