readwise-search
Pass
Audited by Gen Agent Trust Hub on Oct 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes external command-line utilities (
readwiseandreadwise-custom) to interface with the Readwise API. These tools are used as intended for the skill's primary function of retrieving user annotations and documents. - [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it ingests untrusted data from external sources.
- Ingestion points: The skill retrieves text content, notes, and highlights from the Readwise API via CLI commands defined in
SKILL.md. - Boundary markers: No specific delimiters or safety warnings are implemented to differentiate between instructions and retrieved data.
- Capability inventory: The skill is designed for searching and reading library data; it does not exhibit write capabilities or arbitrary code execution based on the data retrieved.
- Sanitization: No sanitization or filtering of the retrieved highlight text is specified in the instructions.
Audit Metadata