weread-skills
Pass
Audited by Gen Agent Trust Hub on Oct 19, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill contains instructions (in SKILL.md) that require the agent to pause operations and follow instructions found within the 'upgrade_info.message' field of any API response from the WeRead gateway.
- Ingestion points: Data ingested through the central API gateway at 'https://i.weread.qq.com/api/agent/gateway' (SKILL.md).
- Boundary markers: The skill does not provide any delimiters or warnings to the agent to ignore potentially malicious instructions embedded in the 'upgrade_info' field.
- Capability inventory: The skill has the capability to perform authenticated API requests, search for books, manage bookshelves, and retrieve user reading statistics across multiple files (book.md, shelf.md, readdata.md).
- Sanitization: There is no defined process for sanitizing or verifying the contents of the upgrade message before the agent acts upon it.
Audit Metadata