reading-digest
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill performs its stated function of document analysis and summarization using a provided MCP server. The operations (reading and creating documents) are restricted to the Yuque platform, which aligns with the skill's purpose and author context.\n- [INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection because it ingests and processes untrusted article content from external sources.\n
- Ingestion points: Article text is ingested via the
yuque_get_doctool or direct user input in SKILL.md.\n - Boundary markers: No explicit delimiters are instructed to be used when interpolating the article text into the analysis prompt.\n
- Capability inventory: The agent can write to persistent storage using the
yuque_create_doctool.\n - Sanitization: There are no instructions for sanitizing or filtering the source content before it is analyzed.
Audit Metadata