share-reading
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external sources which could contain malicious instructions.
- Ingestion points: The skill uses
WebFetchto retrieve content from user-provided URLs andReadto access content from local file paths. - Boundary markers: There are no explicit delimiters or instructions provided to the agent to treat the fetched/read content strictly as data or to ignore any embedded commands within that content.
- Capability inventory: The skill possesses the ability to perform network requests (
WebFetch) and read local files (Read), then uses this data to generate natural language output. - Sanitization: No evidence of sanitization, filtering, or validation of the external content was found before the content is interpolated into the generation process.
Audit Metadata