style-drift
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's primary purpose is text analysis, and its instructions are focused on literary auditing without requesting sensitive permissions or performing dangerous operations.
- [NO_CODE]: The skill consists solely of descriptive instructions and does not contain any scripts, binaries, or automated execution logic.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data in the form of user-provided prose and chapters for analysis.
- Ingestion points: Instructions specify auditing 'chapters, revisions, or new material' (SKILL.md).
- Boundary markers: None identified in the prompt instructions to delimit user content from instructions.
- Capability inventory: The skill writes analysis results to 'style/STYLE_AUDIT.md' but does not possess network access, system modification, or high-privilege file system capabilities.
- Sanitization: No explicit sanitization or filtering of the input text is defined.
Audit Metadata