ebook-discovery
Pass
Audited by Gen Agent Trust Hub on Apr 21, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is comprised of Markdown documentation and structural templates designed to guide an AI agent through a creative process. No executable scripts, obfuscated content, or unauthorized data access patterns were found.
- [COMMAND_EXECUTION]: The instructions do not contain shell commands, system calls, or subprocess executions.
- [DATA_EXFILTRATION]: The skill does not perform any network operations or data transfers to external domains.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external content such as blog posts and newsletters provided by the user, which serves as an ingestion point for untrusted data. However, the skill lacks high-risk capabilities (like network access or arbitrary code execution) that would allow for exploitation. 1. Ingestion points: User-provided content archives such as blog posts and newsletters (SKILL.md). 2. Boundary markers: No explicit delimiters or instructions to ignore embedded commands are provided for processed data. 3. Capability inventory: Local file read/write operations for managing the Discovery Tracker. 4. Sanitization: No sanitization or validation of external content is described.
Audit Metadata