ppt-narrative-review
Pass
Audited by Gen Agent Trust Hub on May 2, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is configured to ingest and analyze user-supplied content such as storylines and slide outlines, creating a surface for indirect prompt injection.
- Ingestion points: Untrusted data is introduced into the agent context when a user provides drafted storylines or chapter directories for review as specified in SKILL.md.
- Boundary markers: The instructions do not define specific delimiters or instructions for the AI to ignore potential commands embedded within the user content.
- Capability inventory: The skill functionality is limited to text analysis and reporting, with no found capabilities for shell command execution, network exfiltration, or file system writes.
- Sanitization: No explicit validation, filtering, or sanitization of the external content is present in the prompt instructions.
Audit Metadata